{
  "aboutHtml": "<p>Nova-3 是 Deepgram 將音訊轉成文字的通用語音辨識模型。提供者建議用於會議、活動字幕、多說話者錄音，以及雜訊或遠距麥克風等困難條件，可採預錄或串流轉錄。實用結果是連結來源音訊的辨識語音，並附時間與信心資訊。</p><h4>選擇語言流程</h4><p>文件所載預設語言是英文。單語請求選擇口述語言或支援地區變體。現行通用模型表包含英文區域變體、西班牙文、法文、德文、俄文、葡萄牙文、日文、義大利文、荷蘭文、阿拉伯文、中文書寫形式及許多其他語言，包括哈薩克文。請從提供者支援的代碼選擇，不要假設任意地區名稱都可接受。</p><p>多語言設定是獨立的語碼轉換流程。現行 Nova-3 表為它列出十種語言：英文、西班牙文、法文、德文、印地文、俄文、葡萄牙文、日文、義大利文與荷蘭文。此集合不同於較大的單語清單。錄音在支援語言間交替時，請準備多語言模式，不要將整段對話強制放入不相符的單語設定。請先保留實際口述內容，再準備翻譯或摘要版本。</p><h4>錄製音訊與逐字稿準備</h4><p>Deepgram 檔案流程接受上傳音訊位元組或音訊檔案參照。請求完成時請儲存回傳逐字稿；提供者不保存逐字稿供後續取回。文件記載的常見輸入格式與編碼包括 MP3、MP4、MP2、AAC、WAV、FLAC、PCM、M4A、Ogg、Opus、WebM。請將實際格式與聲道資訊和錄音一起保留。為錄音設定穩定識別碼，讓結果連結至正確來源及聲道資訊。會議請在聆聽原音時核對參與者姓名與技術用語；講座或活動則保留音訊順序，讓後續字幕或搜尋結果定位相關段落。</p><p>提供者的預錄指南列出最大檔案大小為 2 GB，並建議從大型影片檔擷取音軌。也記載 Nova 請求的十分鐘處理逾時。此逾時是請求處理時間，不是錄音最長十分鐘。實用結果應包含預期錄音的結尾；只保留部分的逐字稿不應視為完整文字。</p><h4>閱讀單字、時間與信心</h4><p>文件所載 JSON 回應包含候選逐字稿與辨識單字，每個單字附自音訊開始計算的開始及結束秒數與信心值。多說話者逐字稿可透過提供者可選的說話者分離，為每個單字指派說話者標籤。預錄說話者分離還回傳說話者信心，串流說話者分離則回傳說話者標籤。請對照錄音聲音審查標籤。整體逐字稿信心也以 0–1 尺度回報。要求智慧格式化時，結果可包含帶標點的單字形式，保留標點與大小寫，並提供可讀段落資訊。</p><p>請依欄位意義使用。單字時間定位辨識語音，信心則是模型對可靠性的指示，不是困難姓名或數量已被正確聽出的證明。準備字幕時，請將時間和審閱過的措辭一起保留，並對照聲音檢查邊界。若準備可讀的編輯版本，請讓修改與辨識逐字稿可區分，不要暗中將不確定單字換成看似合理的故事。</p><h4>串流辨識與最終片段</h4><p>Nova 串流流程會隨音訊到達回傳文字，包括暫時與最終結果。is_final 指標區分仍可能修改的文字與已定稿片段。speech_final 指標則涉及口述片段的終點判定。請將這些訊號與單純收到非空逐字稿區分；準備完整記錄時，按音訊順序保留最終片段。</p><p>Nova-3 是一般 ASR，不是另一個具有模型原生輪次偵測的 Flux 對話模型。Nova 標示逐字稿定稿狀態與語音終點；Flux 提供自己的對話輪次狀態事件。請依音訊已錄製或正即時到達選擇轉錄流程，並將實際最終輸出作為保留產物。</p><h4>為重要詞彙使用 Keyterms</h4><p>Nova-3 文件所載 Keyterm Prompting 支援單語與多語言轉錄，不需重新訓練模型即可讓辨識偏向重要詞彙。請提供可能實際被說出的相關姓名、產品用語、縮寫或多字詞組。指南將合計 keyterm 輸入限制為 500 token，建議聚焦最重要詞彙，不要不加選擇地加入常見詞。</p><p>提供者語法使用純詞彙，每個詞彙各有獨立 keyterm 項目。多字詞組維持一個詞組。舊式 keyword 權重或強化符號，以及用逗號、分號或換行連接獨立詞彙，都不等價：介面可能將其當成單一字面值接受，卻沒有預期加權效果。姓名請使用正確大小寫，之後仍須檢查逐字稿，因為音訊上下文與智慧格式化仍可能改變最終書寫形式。</p><h4>模型家族邊界與實用結果</h4><p>通用 Nova-3 規格不同於另名的 Medical 與 Pharma 選項。詞彙提示不會使它變成另一版本，也不應將專用模型的語言範圍或行為套用至通用模型。額外逐字稿處理功能是提供者語音流程中的選擇，不是辨識已產生未曾要求的摘要、翻譯或其他產物的證據。</p><p>實用 Nova-3 交付物可以是可搜尋會議逐字稿、附逐字時間的字幕準備文字，或多語言對話記錄。請保留音訊識別碼、所選語言流程、最終文字，以及有用的信心或時間欄位。請對照原始錄音檢查不清楚的姓名、數字、重疊聲音與語言切換，讓實際辨識語音仍可供下一個內容處理步驟使用。</p>",
  "aboutText": "Nova-3 是 Deepgram 將音訊轉成文字的通用語音辨識模型。提供者建議用於會議、活動字幕、多說話者錄音，以及雜訊或遠距麥克風等困難條件，可採預錄或串流轉錄。實用結果是連結來源音訊的辨識語音，並附時間與信心資訊。\n\n### 選擇語言流程\n\n文件所載預設語言是英文。單語請求選擇口述語言或支援地區變體。現行通用模型表包含英文區域變體、西班牙文、法文、德文、俄文、葡萄牙文、日文、義大利文、荷蘭文、阿拉伯文、中文書寫形式及許多其他語言，包括哈薩克文。請從提供者支援的代碼選擇，不要假設任意地區名稱都可接受。\n\n多語言設定是獨立的語碼轉換流程。現行 Nova-3 表為它列出十種語言：英文、西班牙文、法文、德文、印地文、俄文、葡萄牙文、日文、義大利文與荷蘭文。此集合不同於較大的單語清單。錄音在支援語言間交替時，請準備多語言模式，不要將整段對話強制放入不相符的單語設定。請先保留實際口述內容，再準備翻譯或摘要版本。\n\n### 錄製音訊與逐字稿準備\n\nDeepgram 檔案流程接受上傳音訊位元組或音訊檔案參照。請求完成時請儲存回傳逐字稿；提供者不保存逐字稿供後續取回。文件記載的常見輸入格式與編碼包括 MP3、MP4、MP2、AAC、WAV、FLAC、PCM、M4A、Ogg、Opus、WebM。請將實際格式與聲道資訊和錄音一起保留。為錄音設定穩定識別碼，讓結果連結至正確來源及聲道資訊。會議請在聆聽原音時核對參與者姓名與技術用語；講座或活動則保留音訊順序，讓後續字幕或搜尋結果定位相關段落。\n\n提供者的預錄指南列出最大檔案大小為 2 GB，並建議從大型影片檔擷取音軌。也記載 Nova 請求的十分鐘處理逾時。此逾時是請求處理時間，不是錄音最長十分鐘。實用結果應包含預期錄音的結尾；只保留部分的逐字稿不應視為完整文字。\n\n### 閱讀單字、時間與信心\n\n文件所載 JSON 回應包含候選逐字稿與辨識單字，每個單字附自音訊開始計算的開始及結束秒數與信心值。多說話者逐字稿可透過提供者可選的說話者分離，為每個單字指派說話者標籤。預錄說話者分離還回傳說話者信心，串流說話者分離則回傳說話者標籤。請對照錄音聲音審查標籤。整體逐字稿信心也以 0–1 尺度回報。要求智慧格式化時，結果可包含帶標點的單字形式，保留標點與大小寫，並提供可讀段落資訊。\n\n請依欄位意義使用。單字時間定位辨識語音，信心則是模型對可靠性的指示，不是困難姓名或數量已被正確聽出的證明。準備字幕時，請將時間和審閱過的措辭一起保留，並對照聲音檢查邊界。若準備可讀的編輯版本，請讓修改與辨識逐字稿可區分，不要暗中將不確定單字換成看似合理的故事。\n\n### 串流辨識與最終片段\n\nNova 串流流程會隨音訊到達回傳文字，包括暫時與最終結果。is_final 指標區分仍可能修改的文字與已定稿片段。speech_final 指標則涉及口述片段的終點判定。請將這些訊號與單純收到非空逐字稿區分；準備完整記錄時，按音訊順序保留最終片段。\n\nNova-3 是一般 ASR，不是另一個具有模型原生輪次偵測的 Flux 對話模型。Nova 標示逐字稿定稿狀態與語音終點；Flux 提供自己的對話輪次狀態事件。請依音訊已錄製或正即時到達選擇轉錄流程，並將實際最終輸出作為保留產物。\n\n### 為重要詞彙使用 Keyterms\n\nNova-3 文件所載 Keyterm Prompting 支援單語與多語言轉錄，不需重新訓練模型即可讓辨識偏向重要詞彙。請提供可能實際被說出的相關姓名、產品用語、縮寫或多字詞組。指南將合計 keyterm 輸入限制為 500 token，建議聚焦最重要詞彙，不要不加選擇地加入常見詞。\n\n提供者語法使用純詞彙，每個詞彙各有獨立 keyterm 項目。多字詞組維持一個詞組。舊式 keyword 權重或強化符號，以及用逗號、分號或換行連接獨立詞彙，都不等價：介面可能將其當成單一字面值接受，卻沒有預期加權效果。姓名請使用正確大小寫，之後仍須檢查逐字稿，因為音訊上下文與智慧格式化仍可能改變最終書寫形式。\n\n### 模型家族邊界與實用結果\n\n通用 Nova-3 規格不同於另名的 Medical 與 Pharma 選項。詞彙提示不會使它變成另一版本，也不應將專用模型的語言範圍或行為套用至通用模型。額外逐字稿處理功能是提供者語音流程中的選擇，不是辨識已產生未曾要求的摘要、翻譯或其他產物的證據。\n\n實用 Nova-3 交付物可以是可搜尋會議逐字稿、附逐字時間的字幕準備文字，或多語言對話記錄。請保留音訊識別碼、所選語言流程、最終文字，以及有用的信心或時間欄位。請對照原始錄音檢查不清楚的姓名、數字、重疊聲音與語言切換，讓實際辨識語音仍可供下一個內容處理步驟使用。",
  "editorialOverlay": {
    "copy_fields": null,
    "copy_sha256": null,
    "copy_source": null,
    "html_sha256": "91230090448b5575e773180ca847285ff560680686ebb0216f4f6c164cf88775",
    "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06",
    "raw_model_unchanged": true,
    "schema": "ailoot-native-model-editorial-v1"
  },
  "locale": "zh-hant-tw",
  "methods": [
    {
      "html": "<div class=\"sheet-head\"><span class=\"mav\" aria-hidden=\"true\">•</span><h2 id=\"sheet-title\">Deepgram: Nova-3</h2><button class=\"icon-btn\" type=\"button\" data-close-sheet aria-label=\"關閉\">×</button></div><div class=\"idline\"><span>Deepgram /</span><code>deepgram/nova-3</code><button type=\"button\" id=\"copy-id\">複製 ID</button></div><nav class=\"card-jump-nav\" aria-label=\"模型卡片區段\"><button type=\"button\" data-card-jump=\"overview\">入門</button><button type=\"button\" data-card-jump=\"methods\">輸入與方法</button><button type=\"button\" data-card-jump=\"pricing\">方案</button><button type=\"button\" data-card-jump=\"examples\">範例</button><button type=\"button\" data-card-jump=\"results\">結果</button><button type=\"button\" data-card-jump=\"aliases\">別名</button></nav><div class=\"card-method-tabs\" role=\"tablist\" aria-label=\"API 方法\"><button type=\"button\" role=\"tab\" tabindex=\"0\" aria-controls=\"card-method-content\" aria-selected=\"true\" id=\"card-method-tab-0\" data-card-method=\"Ultra|transcriptions|/v1/audio/transcriptions|deepgram%2Fnova-3\">辨識</button></div><div id=\"card-method-content\" role=\"tabpanel\" aria-labelledby=\"card-method-tab-0\"><section class=\"card-section\" data-card-section=\"overview\"><h3 tabindex=\"-1\">入門</h3><p class=\"mdesc-full\">Nova-3 是 Deepgram 用於錄製及串流音訊的通用語音轉文字模型。它支援單語辨識、明定的多語言語碼轉換模式及關鍵詞提示，回傳附逐字時間與信心資訊的逐字稿。</p><dl class=\"card-io\" data-card-io><div><dt>接受的輸入</dt><dd>音訊</dd></div><div><dt>結果</dt><dd>transcription</dd></div></dl><details class=\"card-about\"><summary>關於模型</summary><p class=\"note-s\" data-model-method-boundary>此說明介紹模型的能力。Ailoot 可用的輸入、輸出與選項，依所選方法列於下方。</p><div class=\"mabout\" id=\"m-about\"><p>Nova-3 是 Deepgram 將音訊轉成文字的通用語音辨識模型。提供者建議用於會議、活動字幕、多說話者錄音，以及雜訊或遠距麥克風等困難條件，可採預錄或串流轉錄。實用結果是連結來源音訊的辨識語音，並附時間與信心資訊。</p><h4>選擇語言流程</h4><p>文件所載預設語言是英文。單語請求選擇口述語言或支援地區變體。現行通用模型表包含英文區域變體、西班牙文、法文、德文、俄文、葡萄牙文、日文、義大利文、荷蘭文、阿拉伯文、中文書寫形式及許多其他語言，包括哈薩克文。請從提供者支援的代碼選擇，不要假設任意地區名稱都可接受。</p><p>多語言設定是獨立的語碼轉換流程。現行 Nova-3 表為它列出十種語言：英文、西班牙文、法文、德文、印地文、俄文、葡萄牙文、日文、義大利文與荷蘭文。此集合不同於較大的單語清單。錄音在支援語言間交替時，請準備多語言模式，不要將整段對話強制放入不相符的單語設定。請先保留實際口述內容，再準備翻譯或摘要版本。</p><h4>錄製音訊與逐字稿準備</h4><p>Deepgram 檔案流程接受上傳音訊位元組或音訊檔案參照。請求完成時請儲存回傳逐字稿；提供者不保存逐字稿供後續取回。文件記載的常見輸入格式與編碼包括 MP3、MP4、MP2、AAC、WAV、FLAC、PCM、M4A、Ogg、Opus、WebM。請將實際格式與聲道資訊和錄音一起保留。為錄音設定穩定識別碼，讓結果連結至正確來源及聲道資訊。會議請在聆聽原音時核對參與者姓名與技術用語；講座或活動則保留音訊順序，讓後續字幕或搜尋結果定位相關段落。</p><p>提供者的預錄指南列出最大檔案大小為 2 GB，並建議從大型影片檔擷取音軌。也記載 Nova 請求的十分鐘處理逾時。此逾時是請求處理時間，不是錄音最長十分鐘。實用結果應包含預期錄音的結尾；只保留部分的逐字稿不應視為完整文字。</p><h4>閱讀單字、時間與信心</h4><p>文件所載 JSON 回應包含候選逐字稿與辨識單字，每個單字附自音訊開始計算的開始及結束秒數與信心值。多說話者逐字稿可透過提供者可選的說話者分離，為每個單字指派說話者標籤。預錄說話者分離還回傳說話者信心，串流說話者分離則回傳說話者標籤。請對照錄音聲音審查標籤。整體逐字稿信心也以 0–1 尺度回報。要求智慧格式化時，結果可包含帶標點的單字形式，保留標點與大小寫，並提供可讀段落資訊。</p><p>請依欄位意義使用。單字時間定位辨識語音，信心則是模型對可靠性的指示，不是困難姓名或數量已被正確聽出的證明。準備字幕時，請將時間和審閱過的措辭一起保留，並對照聲音檢查邊界。若準備可讀的編輯版本，請讓修改與辨識逐字稿可區分，不要暗中將不確定單字換成看似合理的故事。</p><h4>串流辨識與最終片段</h4><p>Nova 串流流程會隨音訊到達回傳文字，包括暫時與最終結果。is_final 指標區分仍可能修改的文字與已定稿片段。speech_final 指標則涉及口述片段的終點判定。請將這些訊號與單純收到非空逐字稿區分；準備完整記錄時，按音訊順序保留最終片段。</p><p>Nova-3 是一般 ASR，不是另一個具有模型原生輪次偵測的 Flux 對話模型。Nova 標示逐字稿定稿狀態與語音終點；Flux 提供自己的對話輪次狀態事件。請依音訊已錄製或正即時到達選擇轉錄流程，並將實際最終輸出作為保留產物。</p><h4>為重要詞彙使用 Keyterms</h4><p>Nova-3 文件所載 Keyterm Prompting 支援單語與多語言轉錄，不需重新訓練模型即可讓辨識偏向重要詞彙。請提供可能實際被說出的相關姓名、產品用語、縮寫或多字詞組。指南將合計 keyterm 輸入限制為 500 token，建議聚焦最重要詞彙，不要不加選擇地加入常見詞。</p><p>提供者語法使用純詞彙，每個詞彙各有獨立 keyterm 項目。多字詞組維持一個詞組。舊式 keyword 權重或強化符號，以及用逗號、分號或換行連接獨立詞彙，都不等價：介面可能將其當成單一字面值接受，卻沒有預期加權效果。姓名請使用正確大小寫，之後仍須檢查逐字稿，因為音訊上下文與智慧格式化仍可能改變最終書寫形式。</p><h4>模型家族邊界與實用結果</h4><p>通用 Nova-3 規格不同於另名的 Medical 與 Pharma 選項。詞彙提示不會使它變成另一版本，也不應將專用模型的語言範圍或行為套用至通用模型。額外逐字稿處理功能是提供者語音流程中的選擇，不是辨識已產生未曾要求的摘要、翻譯或其他產物的證據。</p><p>實用 Nova-3 交付物可以是可搜尋會議逐字稿、附逐字時間的字幕準備文字，或多語言對話記錄。請保留音訊識別碼、所選語言流程、最終文字，以及有用的信心或時間欄位。請對照原始錄音檢查不清楚的姓名、數字、重疊聲音與語言切換，讓實際辨識語音仍可供下一個內容處理步驟使用。</p></div></details></section><section class=\"card-section\" data-card-section=\"methods\"><h3 tabindex=\"-1\">Ailoot 可用 · 輸入與方法</h3><details class=\"card-method\" open><summary><b>Ailoot Ultra · 語音辨識</b> <code>POST /v1/audio/transcriptions</code></summary><dl class=\"method-capabilities\"><div><dt>輸入</dt><dd><code>audio</code></dd></div><div><dt>輸出</dt><dd><code>transcription</code></dd></div><div><dt>輸出格式</dt><dd>json</dd></div></dl><div class=\"tw\" data-card-parameters data-typed-parameters><table><thead><tr><th>欄位</th><th>類型</th><th>要求</th><th>值與限制</th><th>預設值</th></tr></thead><tbody><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">model</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>string</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>必填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span><div>deepgram/nova-3</div></td><td data-cell-label=\"預設值\" data-default=\"unspecified\"><span class=\"card-cell-label\">預設值</span>—</td></tr><tr data-parameter-availability=\"source_interface\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">input_audio</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>object</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>必填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span></td><td data-cell-label=\"預設值\" data-default=\"unspecified\"><span class=\"card-cell-label\">預設值</span>—</td></tr><tr data-parameter-availability=\"retained_official_STTRequest\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">language</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>string</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>選填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span></td><td data-cell-label=\"預設值\" data-default=\"unspecified\"><span class=\"card-cell-label\">預設值</span>—</td></tr><tr data-parameter-availability=\"retained_official_STTRequest\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">temperature</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>number</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>選填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span><div>最小值: 0</div><div>最大值: 1</div></td><td data-cell-label=\"預設值\" data-default=\"unspecified\"><span class=\"card-cell-label\">預設值</span>—</td></tr><tr data-parameter-availability=\"retained_official_STTRequest\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">response_format</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>string</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>選填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span><div>json, verbose_json</div></td><td data-cell-label=\"預設值\" data-default=\"known\"><span class=\"card-cell-label\">預設值</span>json</td></tr><tr data-parameter-availability=\"retained_official_STTRequest\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">timestamp_granularities</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>array</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>選填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span></td><td data-cell-label=\"預設值\" data-default=\"unspecified\"><span class=\"card-cell-label\">預設值</span>—</td></tr><tr data-parameter-availability=\"retained_official_STTRequest\"><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">provider</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span><code>object</code></td><td data-cell-label=\"要求\"><span class=\"card-cell-label\">要求</span>選填</td><td data-cell-label=\"值與限制\"><span class=\"card-cell-label\">值與限制</span></td><td data-cell-label=\"預設值\" data-default=\"unspecified\"><span class=\"card-cell-label\">預設值</span>—</td></tr></tbody></table></div><details class=\"card-about\" data-material-combinations><summary>輸入素材組合</summary><p class=\"note-s\"><b>speech_to_text</b> · 必填： actual matching-format audio file</p></details><details class=\"note-s\" data-method-contract><summary>方法參數與生命週期</summary><div class=\"tw\" data-card-table=\"contract\"><table><thead><tr><th>參數</th><th>規格</th></tr></thead><tbody><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>content_types</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>application/json, multipart/form-data</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>required</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>model, input_audio</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>material_types</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>audio</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>JSON_audio</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>以 base64 編碼的實際原始音訊位元組，以及相符的格式</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>multipart_required</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>model, file</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>multipart_cap_bytes</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>26214400</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>optional_controls</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>language, temperature, response_format, timestamp_granularities, provider</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>default_response_format</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>json</td></tr><tr><th data-cell-label=\"參數\" scope=\"row\"><span class=\"card-cell-label\">參數</span><code>optional_features</code></th><td data-cell-label=\"規格\"><span class=\"card-cell-label\">規格</span>詳細輸出、diarize/keyterms，以及 URL／較大的內嵌音訊，均須符合確切模型／供應商的能力與費率。</td></tr></tbody></table></div><p>生命週期： <code>synchronous_result_then_owned_library</code></p><p class=\"note-s\"><code>GET /v1/media/tasks/{task_id}</code> · 實際回傳的 task_id 或媒體庫紀錄</p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}/content</code></p><p class=\"note-s\"><code>GET /v1/media/assets</code></p><p class=\"note-s\"><code>GET /v1/media/assets/{asset_id}</code></p><p class=\"note-s\">請使用完全相符的模型與文件記載的輸入欄位。</p><p class=\"note-s\">請保留完整回應、每個實際輸出，以及原始回傳的 ID。</p></details></details></section><section class=\"card-section\" data-card-section=\"pricing\"><h3 tabindex=\"-1\">方案</h3><div data-native-semantic-method=\"v1\" data-tariff-reference-only><p class=\"note-s\" data-rate-support-note>費率資訊不會增加請求選項。支援的參數列於所選方法中。</p><dl data-price-conditions><dt>快速模式</dt><dd>未指定 <span class=\"note-s\">選取快速模式時</span></dd><dt>flex 模式</dt><dd>未指定 <span class=\"note-s\">選取 flex 模式時</span></dd><dt>最高推理強度</dt><dd>未指定 <span class=\"note-s\">最高推理強度採用 default 調整值時</span></dd></dl></div><div data-declared-tariff-pricing><h4>Ailoot 費率</h4><h4>各設定的價格</h4><p class=\"note-s\">請逐一核對各項費用與所列條件。每組互為替代選項的設定只套用一種費率。</p><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>設定</th><th>費率表</th><th>計費單位</th><th>費用</th></tr></thead><tbody><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>基礎 token 費率</th><td data-cell-label=\"費率表\"><span class=\"card-cell-label\">費率表</span>基本費率</td><td data-cell-label=\"計費單位\"><span class=\"card-cell-label\">計費單位</span>—</td><td data-cell-label=\"費用\"><span class=\"card-cell-label\">費用</span><div><span>輸入 · 輸入 Token</span> <b>—</b> <span class=\"price-unit\">/ 1K Token</span></div><div><span>輸出 · 輸出 Token</span> <b>—</b> <span class=\"price-unit\">/ 1K Token</span></div><div><span>輸入 · 讀取快取</span> <b>—</b> <span class=\"price-unit\">/ 1K Token</span></div><div><span>輸入 · 寫入快取</span> <b>—</b> <span class=\"price-unit\">/ 1K Token</span></div><div><span>輸入 · 寫入快取，1 小時</span> <b>—</b> <span class=\"price-unit\">/ 1K Token</span></div></td></tr><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>Ultra</th><td data-cell-label=\"費率表\"><span class=\"card-cell-label\">費率表</span>—</td><td data-cell-label=\"計費單位\"><span class=\"card-cell-label\">計費單位</span>每秒輸入音訊</td><td data-cell-label=\"費用\"><span class=\"card-cell-label\">費用</span><div><span>輸入 · 輸入音訊秒數</span> <b>$0.0001433333333334</b> <span class=\"price-unit\">每秒輸入音訊</span></div></td></tr></tbody></table></div></div><p class=\"note-s\">Ailoot 會在請求前預留估算金額。取得結果後，依實測用量結算最終費用。串流結算採用最終用量紀錄。<a href=\"/docs/zh-hant-tw/billing/reserve/\">預留金額與結算的運作方式 →</a></p><div data-declared-reference-pricing><h4>參考費率詳情</h4><p class=\"note-s\">模型層級的參考費率表不會變更方法選擇、報價或費用。實際計費採用所選 Ailoot 方法的費率。</p><details class=\"card-price-reference\" data-declared-reference-group data-client-selectable=\"false\"><summary>Deepgram: Nova-3</summary><h4>各設定的價格</h4><div class=\"tw\" data-pricing-profiles><table><thead><tr><th>設定</th><th>計費條件</th><th>費用</th></tr></thead><tbody><tr><th data-cell-label=\"設定\" scope=\"row\"><span class=\"card-cell-label\">設定</span>Deepgram: Nova-3 · 預設設定</th><td data-cell-label=\"計費條件\"><span class=\"card-cell-label\">計費條件</span>預設設定</td><td data-cell-label=\"費用\"><span class=\"card-cell-label\">費用</span><div><span>輸入 · 輸入音訊秒數</span> <b>≈US$0.000143</b> <span class=\"price-unit\">每秒輸入音訊</span></div></td></tr></tbody></table></div></details></div></section><section class=\"card-section\" data-card-section=\"examples\"><h3 tabindex=\"-1\">請求範例</h3><h4>Ailoot Ultra · 語音辨識</h4><div class=\"code-group\"><div class=\"cg-bar\"><div class=\"cg-tabs\" role=\"tablist\" aria-label=\"程式碼版本\"><button class=\"cg-tab\" id=\"model-code-1200-tab-0\" role=\"tab\" type=\"button\" aria-controls=\"model-code-1200-panel-0\" aria-selected=\"true\" tabindex=\"0\">curl · 精確的原生請求主體與完整結果</button></div><div class=\"cg-tools\"><button class=\"cg-btn cg-copy\" type=\"button\" aria-label=\"複製程式碼\"><svg class=\"cp\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><rect x=\"5.25\" y=\"5.25\" width=\"8.5\" height=\"8.5\" rx=\"1.75\"/><path d=\"M10.75 5.25V3.5a1.25 1.25 0 0 0-1.25-1.25H3.5A1.25 1.25 0 0 0 2.25 3.5v6a1.25 1.25 0 0 0 1.25 1.25h1.75\"/></svg><svg class=\"ok\" viewBox=\"0 0 16 16\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.4\"><path d=\"m3 8.5 3.25 3.25L13 5\"/></svg></button></div></div><div class=\"cg-body\"><div class=\"cg-pane\" id=\"model-code-1200-panel-0\" role=\"tabpanel\" aria-labelledby=\"model-code-1200-tab-0\"><pre data-lang=\"bash\"><code>set -eu\n: &quot;${AILOOT_API_KEY:?Set your Ailoot API key}&quot;\n: &quot;${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}&quot;\npython3 - &lt;&lt;&#39;PY_REQUEST&#39;\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ[&#39;AILOOT_AUDIO_FILE&#39;]).read_bytes()\nif not (audio[:4]==b&#39;RIFF&#39; and audio[8:12]==b&#39;WAVE&#39;): raise SystemExit(&#39;Supply an actual WAV audio file&#39;)\nif len(audio)&gt;26214400: raise SystemExit(&#39;Use a documented supported large-file flow&#39;)\nrequest={&#39;model&#39;: &#39;deepgram/nova-3&#39;, &#39;input_audio&#39;: {&#39;data&#39;: &#39;${BASE64_ACTUAL_WAV_BYTES}&#39;, &#39;format&#39;: &#39;wav&#39;}}\nrequest[&#39;input_audio&#39;][&#39;data&#39;]=base64.b64encode(audio).decode(&#39;ascii&#39;)\nPath(&#39;request.json&#39;).write_text(json.dumps(request,ensure_ascii=False),encoding=&#39;utf-8&#39;)\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H &quot;Authorization: Bearer $AILOOT_API_KEY&quot; -H &#39;Content-Type: application/json&#39; \\\n  --data-binary @request.json -D response-headers.txt -o response.bin\n# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n</code></pre></div></div></div></section><section class=\"card-section\" data-card-section=\"results\"><h3 tabindex=\"-1\">接收並儲存結果</h3><h4>Ailoot Ultra · 語音辨識</h4><p class=\"note-s\">json</p><ul class=\"card-result-paths\"><li><code>GET /v1/media/tasks/{task_id}</code></li><li><code>GET /v1/media/assets/{asset_id}/content</code></li><li><code>GET /v1/media/assets</code></li><li><code>GET /v1/media/assets/{asset_id}</code></li></ul><div class=\"card-result-process\" data-all-results><h5>保留所有已完成的結果</h5><p class=\"note-s\">請保留所有完整傳回的回應、檔案與內容區塊。</p><p class=\"note-s\">完整的原始 JSON、所有可用的文字／片段／單字／說話者／時間戳記與用量。</p></div><div class=\"card-result-process\" data-unknown-recovery><h5>需要檢查原始回應時</h5><p class=\"note-s\">請保留原始 operation_id/X-Client-Request-ID 與原始回應。請讀取實際的自有工作／資產紀錄，切勿重新提交；此處不會組出專用的音訊輪詢 URL。</p></div><details class=\"card-about\" data-output-fields><summary>回應欄位</summary><div class=\"tw\" data-card-table=\"output\"><table><thead><tr><th>欄位</th><th>類型</th></tr></thead><tbody><tr><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">text</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span>string</td></tr><tr><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">usage</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span>object</td></tr><tr><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">segments[]</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span>object</td></tr><tr><th data-cell-label=\"欄位\" scope=\"row\"><span class=\"card-cell-label\">欄位</span><code class=\"card-field-name\">words[]</code></th><td data-cell-label=\"類型\" data-field-type><span class=\"card-cell-label\">類型</span>object</td></tr></tbody></table></div></details></section><section class=\"card-section\" data-card-section=\"aliases\"><h3 tabindex=\"-1\">別名</h3><h4>模型別名</h4><p class=\"note-s\"><span data-model-alias-route=\"Ultra\"><b>Ailoot Ultra</b> <a href=\"#m=deepgram%2Fnova-3&amp;route=Ultra&amp;caller=deepgram%2Fnova-3&amp;fmt=transcriptions\"><code>deepgram/nova-3</code></a></span></p><h4>方法路徑別名</h4><p class=\"note-s\">請使用上方列出的 API 方法路徑。</p><h4>相關呼叫用 ID</h4><p class=\"note-s\"><a href=\"#m=deepgram%2Fnova-3&amp;route=Ultra&amp;caller=deepgram%2Fnova-3&amp;fmt=transcriptions\"><code>deepgram/nova-3</code></a></p></section></div>",
      "method_identity": {
        "effective_request_model_id": "deepgram/nova-3",
        "fmt": "transcriptions",
        "http": "POST",
        "path": "/v1/audio/transcriptions",
        "request_model_id": "deepgram/nova-3",
        "route_label": "Ultra"
      },
      "method_key": "Ultra|transcriptions|/v1/audio/transcriptions|deepgram%2Fnova-3",
      "ordinal": 0,
      "rawMethod": {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.",
            "lifecycle": {
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "請保留原始 operation_id/X-Client-Request-ID 與原始回應。請讀取實際的自有工作／資產紀錄，切勿重新提交；此處不會組出專用的音訊輪詢 URL。"
            },
            "material_combinations": [
              {
                "content_types": [
                  "application/json",
                  "multipart/form-data"
                ],
                "mode": "speech_to_text",
                "required": [
                  "actual matching-format audio file"
                ]
              }
            ],
            "outputs": {
              "all_results": "完整的原始 JSON、所有可用的文字／片段／單字／說話者／時間戳記與用量。",
              "family": "transcription",
              "fields": [
                {
                  "name": "text",
                  "type": "string"
                },
                {
                  "name": "usage",
                  "type": "object"
                },
                {
                  "name": "segments[]",
                  "optional": true,
                  "type": "object"
                },
                {
                  "name": "words[]",
                  "optional": true,
                  "type": "object"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "enum": [
                  "deepgram/nova-3"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "data_encoding": "base64 raw actual audio bytes, not data URI",
                "fields": [
                  "data",
                  "format"
                ],
                "name": "input_audio",
                "required": true,
                "type": "object"
              },
              {
                "availability": "retained_official_STTRequest",
                "description": "ISO-639-1 code; omitted means auto-detection",
                "name": "language",
                "required": false,
                "type": "string"
              },
              {
                "availability": "retained_official_STTRequest",
                "maximum": 1,
                "minimum": 0,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "retained_official_STTRequest",
                "default": "json",
                "default_known": true,
                "description": "verbose_json requires exact model/provider support",
                "enum": [
                  "json",
                  "verbose_json"
                ],
                "enum_known": true,
                "name": "response_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "retained_official_STTRequest",
                "description": "Only used with supported verbose_json",
                "items": {
                  "enum": [
                    "segment",
                    "word"
                  ],
                  "type": "string"
                },
                "name": "timestamp_granularities",
                "required": false,
                "type": "array"
              },
              {
                "availability": "retained_official_STTRequest",
                "description": "Data policy and exact provider options; order/only/ignore are not applied to STT",
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "request_schema": {
              "properties": {
                "input_audio": {
                  "properties": {
                    "data": {
                      "contentEncoding": "base64",
                      "type": "string"
                    },
                    "format": {
                      "enum": [
                        "wav",
                        "mp3",
                        "flac",
                        "m4a",
                        "ogg",
                        "webm",
                        "aac"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "data",
                    "format"
                  ],
                  "type": "object"
                },
                "language": {
                  "description": "ISO-639-1 code; omitted means auto-detection",
                  "type": "string"
                },
                "model": {
                  "enum": [
                    "deepgram/nova-3"
                  ],
                  "type": "string"
                },
                "provider": {
                  "description": "Data policy and exact provider options; order/only/ignore are not applied to STT",
                  "properties": {
                    "data_collection": {
                      "enum": [
                        "allow",
                        "deny",
                        null
                      ],
                      "type": [
                        "string",
                        "null"
                      ]
                    },
                    "options": {
                      "type": "object"
                    },
                    "zdr": {
                      "type": [
                        "boolean",
                        "null"
                      ]
                    }
                  },
                  "type": "object"
                },
                "response_format": {
                  "default": "json",
                  "description": "verbose_json requires exact model/provider support",
                  "enum": [
                    "json",
                    "verbose_json"
                  ],
                  "type": "string"
                },
                "temperature": {
                  "maximum": 1,
                  "minimum": 0,
                  "type": "number"
                },
                "timestamp_granularities": {
                  "description": "Only used with supported verbose_json",
                  "items": {
                    "enum": [
                      "segment",
                      "word"
                    ],
                    "type": "string"
                  },
                  "type": "array"
                }
              },
              "required": [
                "model",
                "input_audio"
              ],
              "type": "object"
            },
            "schema_template": {
              "actual_file_preparation_required": true,
              "body": {
                "input_audio": {
                  "data": "${BASE64_ACTUAL_WAV_BYTES}",
                  "format": "wav"
                },
                "model": "deepgram/nova-3"
              },
              "content_type": "application/json"
            }
          },
          "hints": [
            "請使用完全相符的模型與文件記載的輸入欄位。",
            "請保留完整回應、每個實際輸出，以及原始回傳的 ID。"
          ],
          "input": {
            "JSON_audio": "以 base64 編碼的實際原始音訊位元組，以及相符的格式",
            "content_types": [
              "application/json",
              "multipart/form-data"
            ],
            "default_response_format": "json",
            "material_types": [
              "audio"
            ],
            "multipart_cap_bytes": 26214400,
            "multipart_required": [
              "model",
              "file"
            ],
            "optional_controls": [
              "language",
              "temperature",
              "response_format",
              "timestamp_granularities",
              "provider"
            ],
            "optional_features": "詳細輸出、diarize/keyterms，以及 URL／較大的內嵌音訊，均須符合確切模型／供應商的能力與費率。",
            "required": [
              "model",
              "input_audio"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "實際回傳的 task_id 或媒體庫紀錄",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Retain original operation_id/X-Client-Request-ID and original response. Read actual owned task/asset records without resubmitting; no dedicated audio poll URL is constructed."
          },
          "method": {
            "http": "POST",
            "path": "/v1/audio/transcriptions"
          },
          "method_aliases": [],
          "operation_modes": [
            "speech_to_text"
          ],
          "output": {
            "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.",
            "family": "transcription",
            "format": "json"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quantity_basis": "actual physical units",
              "quoted_unit": "per audio input second"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.0001433333333334",
                "amount_unit": "usd_per_audio_input_second",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_second",
                "label": "audio input second",
                "native_amount_usd_per_unit": "0.0001433333333334",
                "native_quantity": 1,
                "public_unit_label": "per audio input second",
                "quantity": "1",
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_second"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'deepgram/nova-3', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}}\nrequest['input_audio']['data']=base64.b64encode(audio).decode('ascii')\nPath('request.json').write_text(json.dumps(request,ensure_ascii=False),encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o response.bin\n# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n",
            "label": "curl · exact native body and complete result",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "transcriptions",
        "hints": [
          "Use the exact model and documented input fields.",
          "Keep the complete response, every actual output and original returned IDs."
        ],
        "http": "POST",
        "in": null,
        "input": [
          "audio"
        ],
        "label": "Распознавание речи",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": null,
        "output": [
          "transcription"
        ],
        "path": "/v1/audio/transcriptions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "per_request",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null,
          "unit_prices": {
            "audio_input_second": 0.0001433333333334
          }
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quantity_basis": "actual physical units",
              "quoted_unit": "per audio input second"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.0001433333333334",
                "amount_unit": "usd_per_audio_input_second",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_second",
                "label": "audio input second",
                "native_amount_usd_per_unit": "0.0001433333333334",
                "native_quantity": 1,
                "public_unit_label": "per audio input second",
                "quantity": "1",
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_second"
              }
            ]
          }
        ],
        "request_model_id": "deepgram/nova-3",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}",
          "GET /v1/media/assets/{asset_id}/content"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.0001433333333334",
            "amount_unit": "usd_per_audio_input_second",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_input_second",
            "label": "audio input second",
            "native_amount_usd_per_unit": "0.0001433333333334",
            "native_quantity": 1,
            "public_unit_label": "per audio input second",
            "quantity": "1",
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "audio_input_second"
          }
        ]
      }
    }
  ],
  "model_id": "deepgram/nova-3",
  "nativeProvenance": {
    "input_facts_canonical_sha256": "d8035a7a909349ab413c5365fc555ae381f4e2b122d82bbd066fe39a5eff6306",
    "input_html_sha256": "98467614951f0ccc6bc3243e7a638b5bc4e51d39e5d8576963995ed33ba3250c",
    "private_audit_sha256": "c0355e10f3f27671cff69eaa4d033009cd53fa7010a7112f4f459efd32a06c16",
    "role": "historical-normalized-input-audit-hashes",
    "schema": "ailoot-native-model-provenance-v2"
  },
  "page": {
    "canonical": "https://ailoot.ai/models/zh-hant-tw/deepgram-nova-3/",
    "description": "Nova-3 是 Deepgram 用於錄製及串流音訊的通用語音轉文字模型。它支援單語辨識、明定的多語言語碼轉換模式及關鍵詞提示，回傳附逐字時間與信心資訊的逐字稿。",
    "locale": "zh-hant-tw",
    "md_url": "https://ailoot.ai/models/zh-hant-tw/deepgram-nova-3/index.md",
    "title": "Deepgram: Nova-3 — Ailoot",
    "url": "https://ailoot.ai/models/zh-hant-tw/deepgram-nova-3/"
  },
  "rawModel": {
    "about": "Nova-3 是 Deepgram 將音訊轉成文字的通用語音辨識模型。提供者建議用於會議、活動字幕、多說話者錄音，以及雜訊或遠距麥克風等困難條件，可採預錄或串流轉錄。實用結果是連結來源音訊的辨識語音，並附時間與信心資訊。\n\n### 選擇語言流程\n\n文件所載預設語言是英文。單語請求選擇口述語言或支援地區變體。現行通用模型表包含英文區域變體、西班牙文、法文、德文、俄文、葡萄牙文、日文、義大利文、荷蘭文、阿拉伯文、中文書寫形式及許多其他語言，包括哈薩克文。請從提供者支援的代碼選擇，不要假設任意地區名稱都可接受。\n\n多語言設定是獨立的語碼轉換流程。現行 Nova-3 表為它列出十種語言：英文、西班牙文、法文、德文、印地文、俄文、葡萄牙文、日文、義大利文與荷蘭文。此集合不同於較大的單語清單。錄音在支援語言間交替時，請準備多語言模式，不要將整段對話強制放入不相符的單語設定。請先保留實際口述內容，再準備翻譯或摘要版本。\n\n### 錄製音訊與逐字稿準備\n\nDeepgram 檔案流程接受上傳音訊位元組或音訊檔案參照。請求完成時請儲存回傳逐字稿；提供者不保存逐字稿供後續取回。文件記載的常見輸入格式與編碼包括 MP3、MP4、MP2、AAC、WAV、FLAC、PCM、M4A、Ogg、Opus、WebM。請將實際格式與聲道資訊和錄音一起保留。為錄音設定穩定識別碼，讓結果連結至正確來源及聲道資訊。會議請在聆聽原音時核對參與者姓名與技術用語；講座或活動則保留音訊順序，讓後續字幕或搜尋結果定位相關段落。\n\n提供者的預錄指南列出最大檔案大小為 2 GB，並建議從大型影片檔擷取音軌。也記載 Nova 請求的十分鐘處理逾時。此逾時是請求處理時間，不是錄音最長十分鐘。實用結果應包含預期錄音的結尾；只保留部分的逐字稿不應視為完整文字。\n\n### 閱讀單字、時間與信心\n\n文件所載 JSON 回應包含候選逐字稿與辨識單字，每個單字附自音訊開始計算的開始及結束秒數與信心值。多說話者逐字稿可透過提供者可選的說話者分離，為每個單字指派說話者標籤。預錄說話者分離還回傳說話者信心，串流說話者分離則回傳說話者標籤。請對照錄音聲音審查標籤。整體逐字稿信心也以 0–1 尺度回報。要求智慧格式化時，結果可包含帶標點的單字形式，保留標點與大小寫，並提供可讀段落資訊。\n\n請依欄位意義使用。單字時間定位辨識語音，信心則是模型對可靠性的指示，不是困難姓名或數量已被正確聽出的證明。準備字幕時，請將時間和審閱過的措辭一起保留，並對照聲音檢查邊界。若準備可讀的編輯版本，請讓修改與辨識逐字稿可區分，不要暗中將不確定單字換成看似合理的故事。\n\n### 串流辨識與最終片段\n\nNova 串流流程會隨音訊到達回傳文字，包括暫時與最終結果。is_final 指標區分仍可能修改的文字與已定稿片段。speech_final 指標則涉及口述片段的終點判定。請將這些訊號與單純收到非空逐字稿區分；準備完整記錄時，按音訊順序保留最終片段。\n\nNova-3 是一般 ASR，不是另一個具有模型原生輪次偵測的 Flux 對話模型。Nova 標示逐字稿定稿狀態與語音終點；Flux 提供自己的對話輪次狀態事件。請依音訊已錄製或正即時到達選擇轉錄流程，並將實際最終輸出作為保留產物。\n\n### 為重要詞彙使用 Keyterms\n\nNova-3 文件所載 Keyterm Prompting 支援單語與多語言轉錄，不需重新訓練模型即可讓辨識偏向重要詞彙。請提供可能實際被說出的相關姓名、產品用語、縮寫或多字詞組。指南將合計 keyterm 輸入限制為 500 token，建議聚焦最重要詞彙，不要不加選擇地加入常見詞。\n\n提供者語法使用純詞彙，每個詞彙各有獨立 keyterm 項目。多字詞組維持一個詞組。舊式 keyword 權重或強化符號，以及用逗號、分號或換行連接獨立詞彙，都不等價：介面可能將其當成單一字面值接受，卻沒有預期加權效果。姓名請使用正確大小寫，之後仍須檢查逐字稿，因為音訊上下文與智慧格式化仍可能改變最終書寫形式。\n\n### 模型家族邊界與實用結果\n\n通用 Nova-3 規格不同於另名的 Medical 與 Pharma 選項。詞彙提示不會使它變成另一版本，也不應將專用模型的語言範圍或行為套用至通用模型。額外逐字稿處理功能是提供者語音流程中的選擇，不是辨識已產生未曾要求的摘要、翻譯或其他產物的證據。\n\n實用 Nova-3 交付物可以是可搜尋會議逐字稿、附逐字時間的字幕準備文字，或多語言對話記錄。請保留音訊識別碼、所選語言流程、最終文字，以及有用的信心或時間欄位。請對照原始錄音檢查不清楚的姓名、數字、重疊聲音與語言切換，讓實際辨識語音仍可供下一個內容處理步驟使用。",
    "alias_of": null,
    "aliases": [],
    "author": "Deepgram",
    "available": null,
    "canonical_model": "deepgram/nova-3",
    "capabilities": {
      "context_length": 0,
      "manufacturer_input": [
        "audio"
      ],
      "manufacturer_output": [
        "transcription"
      ]
    },
    "card_routes": [
      {
        "label": "Ultra",
        "rates": [
          {
            "amount": "0.0001433333333334",
            "amount_unit": "usd_per_audio_input_second",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_input_second",
            "label": "audio input second",
            "native_amount_usd_per_unit": "0.0001433333333334",
            "native_quantity": 1,
            "public_unit_label": "per audio input second",
            "quantity": "1",
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "audio_input_second"
          }
        ],
        "summary": "完整的設定價格資訊請見詳細資料。"
      }
    ],
    "ctx": null,
    "declared_tariff_references": [
      {
        "client_selectable": false,
        "key": "c81fd216735cb75857ec",
        "label": "Deepgram: Nova-3",
        "profiles": [
          {
            "basis": "",
            "dimensions": {
              "conditions": "預設設定"
            },
            "label": "Deepgram: Nova-3 · 預設設定",
            "units": [
              {
                "amount": "0.0001433333333334",
                "amount_unit": "usd_per_exact_physical_unit",
                "billing_input": false,
                "key": "ce3ba3a9b22ee118a269edd4",
                "label": "Input audio seconds",
                "public_unit_label": "per input audio second",
                "quantity": "1",
                "rate_role": "declared_tariff_rate",
                "side": "in",
                "unit": "input_audio_second"
              }
            ]
          }
        ]
      }
    ],
    "entity_type": "model",
    "formats": [
      "transcriptions"
    ],
    "id": "deepgram/nova-3",
    "input": [
      "audio"
    ],
    "kind": "transcription",
    "max_out": null,
    "methods": [
      {
        "available": null,
        "cache_read": null,
        "cache_write": null,
        "cache_write_1h": null,
        "contract": {
          "data": {
            "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.",
            "lifecycle": {
              "assets": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets"
                },
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}"
                }
              ],
              "content": [
                {
                  "http": "GET",
                  "path": "/v1/media/assets/{asset_id}/content",
                  "url_source": "exact returned signed URL; never construct token"
                }
              ],
              "mode": "synchronous_result_then_owned_library",
              "operation_id_is_not_task_id": true,
              "status": [
                {
                  "http": "GET",
                  "id_source": "actual returned task_id or media library record",
                  "path": "/v1/media/tasks/{task_id}"
                }
              ],
              "unknown": "請保留原始 operation_id/X-Client-Request-ID 與原始回應。請讀取實際的自有工作／資產紀錄，切勿重新提交；此處不會組出專用的音訊輪詢 URL。"
            },
            "material_combinations": [
              {
                "content_types": [
                  "application/json",
                  "multipart/form-data"
                ],
                "mode": "speech_to_text",
                "required": [
                  "actual matching-format audio file"
                ]
              }
            ],
            "outputs": {
              "all_results": "完整的原始 JSON、所有可用的文字／片段／單字／說話者／時間戳記與用量。",
              "family": "transcription",
              "fields": [
                {
                  "name": "text",
                  "type": "string"
                },
                {
                  "name": "usage",
                  "type": "object"
                },
                {
                  "name": "segments[]",
                  "optional": true,
                  "type": "object"
                },
                {
                  "name": "words[]",
                  "optional": true,
                  "type": "object"
                }
              ],
              "format": "json"
            },
            "parameters": [
              {
                "availability": "source_interface",
                "enum": [
                  "deepgram/nova-3"
                ],
                "enum_known": true,
                "name": "model",
                "required": true,
                "type": "string"
              },
              {
                "availability": "source_interface",
                "data_encoding": "base64 raw actual audio bytes, not data URI",
                "fields": [
                  "data",
                  "format"
                ],
                "name": "input_audio",
                "required": true,
                "type": "object"
              },
              {
                "availability": "retained_official_STTRequest",
                "description": "ISO-639-1 code; omitted means auto-detection",
                "name": "language",
                "required": false,
                "type": "string"
              },
              {
                "availability": "retained_official_STTRequest",
                "maximum": 1,
                "minimum": 0,
                "name": "temperature",
                "required": false,
                "type": "number"
              },
              {
                "availability": "retained_official_STTRequest",
                "default": "json",
                "default_known": true,
                "description": "verbose_json requires exact model/provider support",
                "enum": [
                  "json",
                  "verbose_json"
                ],
                "enum_known": true,
                "name": "response_format",
                "required": false,
                "type": "string"
              },
              {
                "availability": "retained_official_STTRequest",
                "description": "Only used with supported verbose_json",
                "items": {
                  "enum": [
                    "segment",
                    "word"
                  ],
                  "type": "string"
                },
                "name": "timestamp_granularities",
                "required": false,
                "type": "array"
              },
              {
                "availability": "retained_official_STTRequest",
                "description": "Data policy and exact provider options; order/only/ignore are not applied to STT",
                "name": "provider",
                "required": false,
                "type": "object"
              }
            ],
            "request_schema": {
              "properties": {
                "input_audio": {
                  "properties": {
                    "data": {
                      "contentEncoding": "base64",
                      "type": "string"
                    },
                    "format": {
                      "enum": [
                        "wav",
                        "mp3",
                        "flac",
                        "m4a",
                        "ogg",
                        "webm",
                        "aac"
                      ],
                      "type": "string"
                    }
                  },
                  "required": [
                    "data",
                    "format"
                  ],
                  "type": "object"
                },
                "language": {
                  "description": "ISO-639-1 code; omitted means auto-detection",
                  "type": "string"
                },
                "model": {
                  "enum": [
                    "deepgram/nova-3"
                  ],
                  "type": "string"
                },
                "provider": {
                  "description": "Data policy and exact provider options; order/only/ignore are not applied to STT",
                  "properties": {
                    "data_collection": {
                      "enum": [
                        "allow",
                        "deny",
                        null
                      ],
                      "type": [
                        "string",
                        "null"
                      ]
                    },
                    "options": {
                      "type": "object"
                    },
                    "zdr": {
                      "type": [
                        "boolean",
                        "null"
                      ]
                    }
                  },
                  "type": "object"
                },
                "response_format": {
                  "default": "json",
                  "description": "verbose_json requires exact model/provider support",
                  "enum": [
                    "json",
                    "verbose_json"
                  ],
                  "type": "string"
                },
                "temperature": {
                  "maximum": 1,
                  "minimum": 0,
                  "type": "number"
                },
                "timestamp_granularities": {
                  "description": "Only used with supported verbose_json",
                  "items": {
                    "enum": [
                      "segment",
                      "word"
                    ],
                    "type": "string"
                  },
                  "type": "array"
                }
              },
              "required": [
                "model",
                "input_audio"
              ],
              "type": "object"
            },
            "schema_template": {
              "actual_file_preparation_required": true,
              "body": {
                "input_audio": {
                  "data": "${BASE64_ACTUAL_WAV_BYTES}",
                  "format": "wav"
                },
                "model": "deepgram/nova-3"
              },
              "content_type": "application/json"
            }
          },
          "hints": [
            "請使用完全相符的模型與文件記載的輸入欄位。",
            "請保留完整回應、每個實際輸出，以及原始回傳的 ID。"
          ],
          "input": {
            "JSON_audio": "以 base64 編碼的實際原始音訊位元組，以及相符的格式",
            "content_types": [
              "application/json",
              "multipart/form-data"
            ],
            "default_response_format": "json",
            "material_types": [
              "audio"
            ],
            "multipart_cap_bytes": 26214400,
            "multipart_required": [
              "model",
              "file"
            ],
            "optional_controls": [
              "language",
              "temperature",
              "response_format",
              "timestamp_granularities",
              "provider"
            ],
            "optional_features": "詳細輸出、diarize/keyterms，以及 URL／較大的內嵌音訊，均須符合確切模型／供應商的能力與費率。",
            "required": [
              "model",
              "input_audio"
            ]
          },
          "lifecycle": {
            "assets": [
              {
                "http": "GET",
                "path": "/v1/media/assets"
              },
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}"
              }
            ],
            "content": [
              {
                "http": "GET",
                "path": "/v1/media/assets/{asset_id}/content",
                "url_source": "exact returned signed URL; never construct token"
              }
            ],
            "mode": "synchronous_result_then_owned_library",
            "operation_id_is_not_task_id": true,
            "status": [
              {
                "http": "GET",
                "id_source": "實際回傳的 task_id 或媒體庫紀錄",
                "path": "/v1/media/tasks/{task_id}"
              }
            ],
            "unknown": "Retain original operation_id/X-Client-Request-ID and original response. Read actual owned task/asset records without resubmitting; no dedicated audio poll URL is constructed."
          },
          "method": {
            "http": "POST",
            "path": "/v1/audio/transcriptions"
          },
          "method_aliases": [],
          "operation_modes": [
            "speech_to_text"
          ],
          "output": {
            "all_results": "Complete original JSON, all available text/segments/words/speakers/timestamps and usage.",
            "family": "transcription",
            "format": "json"
          }
        },
        "ctx": null,
        "declared_pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quantity_basis": "actual physical units",
              "quoted_unit": "per audio input second"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.0001433333333334",
                "amount_unit": "usd_per_audio_input_second",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_second",
                "label": "audio input second",
                "native_amount_usd_per_unit": "0.0001433333333334",
                "native_quantity": 1,
                "public_unit_label": "per audio input second",
                "quantity": "1",
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_second"
              }
            ]
          }
        ],
        "examples": [
          {
            "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual WAV recording}\"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\nimport base64\naudio=Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4]==b'RIFF' and audio[8:12]==b'WAVE'): raise SystemExit('Supply an actual WAV audio file')\nif len(audio)>26214400: raise SystemExit('Use a documented supported large-file flow')\nrequest={'model': 'deepgram/nova-3', 'input_audio': {'data': '${BASE64_ACTUAL_WAV_BYTES}', 'format': 'wav'}}\nrequest['input_audio']['data']=base64.b64encode(audio).decode('ascii')\nPath('request.json').write_text(json.dumps(request,ensure_ascii=False),encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n  --data-binary @request.json -D response-headers.txt -o response.bin\n# Keep the complete original response and headers. Read every returned segment, word and usage field.\n# Preserve actual operation/task/asset IDs; continue reads of the original result without resubmitting.\n",
            "label": "curl · exact native body and complete result",
            "language": "bash"
          }
        ],
        "family": "openai",
        "fast_multiplier": null,
        "flex_multiplier": null,
        "fmt": "transcriptions",
        "hints": [
          "Use the exact model and documented input fields.",
          "Keep the complete response, every actual output and original returned IDs."
        ],
        "http": "POST",
        "in": null,
        "input": [
          "audio"
        ],
        "label": "Распознавание речи",
        "max_out": null,
        "max_reasoning_effort_multiplier": null,
        "method_aliases": [],
        "out": null,
        "output": [
          "transcription"
        ],
        "path": "/v1/audio/transcriptions",
        "price_conditions": [
          {
            "label": "Fast mode",
            "value": "Not specified",
            "when": "When fast mode is selected"
          },
          {
            "label": "Flex mode",
            "value": "Not specified",
            "when": "When flex mode is selected"
          },
          {
            "label": "Maximum reasoning effort",
            "value": "Not specified",
            "when": "When maximum reasoning effort uses the default adjustment"
          }
        ],
        "pricing": {
          "billing_mode": "per_request",
          "image_input_price": null,
          "image_output_price": null,
          "per_request_price": null,
          "unit_prices": {
            "audio_input_second": 0.0001433333333334
          }
        },
        "pricing_profiles": [
          {
            "dimensions": {
              "regime": "base"
            },
            "label": "Base token rates",
            "units": [
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "input_price",
                "label": "Input tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "output_price",
                "label": "Output tokens",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "output_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "out",
                "unit": "output_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_read_price",
                "label": "Cache read",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "cached_input_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "cached_input_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_price",
                "label": "Cache write",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "generic_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "generic_cache_creation_token"
              },
              {
                "amount": null,
                "amount_unit": "usd_per_thousand_tokens",
                "billing_input": true,
                "estimate_only": false,
                "key": "cache_write_1h_price",
                "label": "Cache write, 1 hour",
                "native_amount_usd_per_unit": null,
                "native_quantity": 1,
                "native_unit": "one_hour_cache_creation_token",
                "public_unit_label": "/ 1K tokens",
                "quantity": 1000,
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "one_hour_cache_creation_token"
              }
            ]
          },
          {
            "dimensions": {
              "quantity_basis": "actual physical units",
              "quoted_unit": "per audio input second"
            },
            "label": "Ultra",
            "units": [
              {
                "amount": "0.0001433333333334",
                "amount_unit": "usd_per_audio_input_second",
                "billing_input": true,
                "estimate_only": false,
                "key": "audio_input_second",
                "label": "audio input second",
                "native_amount_usd_per_unit": "0.0001433333333334",
                "native_quantity": 1,
                "public_unit_label": "per audio input second",
                "quantity": "1",
                "quantity_is_estimate": false,
                "rate_role": "typed_native_retail_rate",
                "side": "in",
                "unit": "audio_input_second"
              }
            ]
          }
        ],
        "request_model_id": "deepgram/nova-3",
        "route_label": "Ultra",
        "status_reads": [
          "GET /v1/media/tasks/{task_id}",
          "GET /v1/media/assets/{asset_id}/content"
        ],
        "tiers": [],
        "units": [
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "input_price",
            "label": "Input tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "output_price",
            "label": "Output tokens",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "output_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "out",
            "unit": "output_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_read_price",
            "label": "Cache read",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "cached_input_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "cached_input_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_price",
            "label": "Cache write",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "generic_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "generic_cache_creation_token"
          },
          {
            "amount": null,
            "amount_unit": "usd_per_thousand_tokens",
            "billing_input": true,
            "estimate_only": false,
            "key": "cache_write_1h_price",
            "label": "Cache write, 1 hour",
            "native_amount_usd_per_unit": null,
            "native_quantity": 1,
            "native_unit": "one_hour_cache_creation_token",
            "public_unit_label": "/ 1K tokens",
            "quantity": 1000,
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "one_hour_cache_creation_token"
          },
          {
            "amount": "0.0001433333333334",
            "amount_unit": "usd_per_audio_input_second",
            "billing_input": true,
            "estimate_only": false,
            "key": "audio_input_second",
            "label": "audio input second",
            "native_amount_usd_per_unit": "0.0001433333333334",
            "native_quantity": 1,
            "public_unit_label": "per audio input second",
            "quantity": "1",
            "quantity_is_estimate": false,
            "rate_role": "typed_native_retail_rate",
            "side": "in",
            "unit": "audio_input_second"
          }
        ]
      }
    ],
    "model_aliases": [
      {
        "canonical_model_id": "deepgram/nova-3",
        "request_model_id": "deepgram/nova-3",
        "route_label": "Ultra"
      }
    ],
    "name": "Deepgram: Nova-3",
    "price": {
      "in": null,
      "in_label": null,
      "out": null,
      "out_label": null,
      "sort_in": null,
      "sort_out": null,
      "varies": true
    },
    "pricing_profiles": [
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "language_variant": "monolingual",
          "multichannel_billing": "requires channel quantity; not implied by one file",
          "payg": true
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0086",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "language_variant": "monolingual",
              "multichannel_billing": "requires channel quantity; not implied by one file",
              "payg": true
            },
            "key": "base",
            "label": "base",
            "profile_index": 0,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "language_variant": "multilingual",
          "multichannel_billing": "requires channel quantity; not implied by one file",
          "payg": true
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0104",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "language_variant": "multilingual",
              "multichannel_billing": "requires channel quantity; not implied by one file",
              "payg": true
            },
            "key": "base",
            "label": "base",
            "profile_index": 1,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "redaction"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0040",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "redaction"
            },
            "key": "redaction",
            "label": "redaction",
            "profile_index": 2,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "keyterm_prompting"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0026",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "keyterm_prompting"
            },
            "key": "keyterm_prompting",
            "label": "keyterm prompting",
            "profile_index": 3,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "in",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "entity_detection"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0034",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "entity_detection"
            },
            "key": "entity_detection",
            "label": "entity detection",
            "profile_index": 4,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "language_variant": "monolingual",
          "multichannel_billing": "requires channel quantity; not implied by one file",
          "payg": true
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0154",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "language_variant": "monolingual",
              "multichannel_billing": "requires channel quantity; not implied by one file",
              "payg": true
            },
            "key": "base",
            "label": "base",
            "profile_index": 5,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "language_variant": "multilingual",
          "multichannel_billing": "requires channel quantity; not implied by one file",
          "payg": true
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0184",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "language_variant": "multilingual",
              "multichannel_billing": "requires channel quantity; not implied by one file",
              "payg": true
            },
            "key": "base",
            "label": "base",
            "profile_index": 6,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "redaction"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0040",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "redaction"
            },
            "key": "redaction",
            "label": "redaction",
            "profile_index": 7,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "keyterm_prompting"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0026",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "keyterm_prompting"
            },
            "key": "keyterm_prompting",
            "label": "keyterm prompting",
            "profile_index": 8,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "in",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "entity_detection"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0034",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "entity_detection"
            },
            "key": "entity_detection",
            "label": "entity detection",
            "profile_index": 9,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      },
      {
        "applicability": {
          "client_selectable": false,
          "native_profile_selection_pending": true,
          "scope": "manufacturer_reference"
        },
        "dimensions": {
          "adds_to_base": true,
          "feature_enabled": "speaker_diarization"
        },
        "label": "Ultra",
        "units": [
          {
            "amount": "0.0040",
            "amount_unit": "usd_per_audio_input_minute",
            "conditions": {
              "adds_to_base": true,
              "feature_enabled": "speaker_diarization"
            },
            "key": "speaker_diarization",
            "label": "speaker diarization",
            "profile_index": 10,
            "quantity": "1",
            "rate_role": "binding_component_rate",
            "side": "out",
            "unit": "audio_input_minute"
          }
        ]
      }
    ],
    "public_id": "deepgram/nova-3",
    "short": "Nova-3 是 Deepgram 用於錄製及串流音訊的通用語音轉文字模型。它支援單語辨識、明定的多語言語碼轉換模式及關鍵詞提示，回傳附逐字時間與信心資訊的逐字稿。"
  },
  "renderer_schema": {
    "method_order": "Original DTO methods order; every exact route/format/path/caller survives.",
    "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers."
  },
  "representation": "exact-public-dto-and-native-renderer-html",
  "representationNotes": {
    "current_reference": {
      "about_json_pointer": "/aboutHtml",
      "methods": [
        {
          "contract_json_pointer": "/methods/0/rawMethod/contract",
          "html_json_pointer": "/methods/0/html",
          "method_ordinal": 0
        }
      ],
      "role": "current-semantic-reference"
    },
    "raw_input": {
      "examples_role": "historical-input-not-current-ready-examples",
      "json_pointers": [
        "/rawModel",
        "/methods/0/rawMethod"
      ],
      "role": "historical-owner-input"
    },
    "schema": "ailoot-native-model-representations-v1"
  },
  "schema": "ailoot-static-model-facts-v1",
  "schema_version": 1,
  "shortText": "Nova-3 是 Deepgram 用於錄製及串流音訊的通用語音轉文字模型。它支援單語辨識、明定的多語言語碼轉換模式及關鍵詞提示，回傳附逐字時間與信心資訊的逐字稿。",
  "source": {
    "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1",
    "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036",
    "raw_model_json_sha256": "cfa2c32bb1fdd119d3b485bee8b38b50e7fabf22132970c1c3163337f2694bc9",
    "renderer_sha256": "13a3fc1b22d07359278e2249d630bfc9bb9e6416c71ba53def933fb5a903660b"
  },
  "sourceRevision": "1ebb787d62fb6f2d0e8c606173c51c971fa5d17f29f84f814d1d97dc1514c83a"
}