{ "aboutHtml": "

GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它接受音訊及可選的文字引導，產生辨識文字。它與使用 GPT-4o 的 GPT-4o Transcribe，以及具有獨立關鍵字與多語言提示欄位、較新的 GPT Transcribe 設定檔，是不同模型。這裡有用的成品是錄音原始發言的逐字稿，可用於搜尋、檢閱或後續內容處理步驟。

準備錄音

OpenAI 的檔案轉錄指南接受最多 25 MB 的音訊上傳。目前的端點參考列出 FLAC、MP3、MP4、MPEG、MPGA、M4A、OGG、WAV 與 WebM，並要求足夠的檔名與內容類型中繼資料，以識別音訊格式。較大的錄音可壓縮或分成每個不超過 25 MB 的部分。分割時保留句子邊界，並讓各部分連到來源錄音與位置，以便之後依正確順序組合文字。

語音筆記應為每份錄音保留一份可識別的逐字稿，並在用文字建立任務前確認名稱或數字。口述教學應在為發布而編輯前，先將辨識用字與原始指示對照。有用的準備說明會指出發言語言及可能聽錯的術語。轉錄字句是第一步；之後可用檢查過的逐字稿進行解讀、摘要或翻譯。

提示詞引導與單一語言提示

既有 GPT-4o Mini Transcribe 整合支援自由形式提示詞。OpenAI 描述可用提示詞提供名稱、縮寫、錄音專用詞彙、標點、大小寫、語助填充詞及偏好的書寫系統。端點參考表示提示詞應符合音訊語言，並可攜帶前一音訊片段的脈絡。加入相關拼法或簡短主題說明，不要要求轉錄提示詞像不受限制的聊天指示一樣運作。

這個模型既有的語言提示使用單數 language 欄位。開發商參考文件記載 ISO 639-1 輸入語言代碼，例如 en。獨立的 keywords 與複數 languages 欄位是 GPT Transcribe 的文件內容，並非這個 Mini 設定檔的一部分。多份錄音應讓各輸入保留預定的發言語言設定，不要將其解讀成翻譯結果的請求。

JSON 結果與可選 token 機率

目前的端點參考將 JSON 記為 GPT-4o Mini Transcribe 支援的回應格式。辨識用字顯示於 text 欄位。要求時，JSON 回應可附帶 token 對數機率；這些值描述模型的 token 機率，並可協助找出需要仔細檢閱的素材。它們無法證明名稱、數字或句子符合聲音。應依錄音判斷可疑字詞是否需要修正。

一般 Mini 轉錄設定檔不會透過這個 JSON 規格提供原生 SRT、VTT、詳細逐字時間戳或附說話者標籤的輸出。OpenAI 為這些能力記載了專用模型與格式。若預定成品是字幕軌，應保留檢閱過的逐字稿，供獨立時間標記流程使用，不要假設純文字結果已包含字幕邊界。

檔案輸出串流與文件記載模式

開發商的語音轉文字指南明確表示，既有 GPT-4o Mini Transcribe 整合支援檔案串流。已完成錄音可在處理時先產生部分逐字稿文字，再產生最終結果。將最終逐字稿保留為完成成品；出現部分文字不代表檔案流程正在持續接收即時麥克風音訊。模型卡另列轉錄與 Realtime 端點家族。這些開發商介面不代表其他轉錄模型的所有工作階段欄位都適用於此。

上下文、輸出額度與實用檢查

OpenAI 目前的模型規格列出 16,000 個 token 的上下文視窗、2,000 個 token 的最大輸出，以及 2024 年 6 月 1 日的知識截止日。這些是模型規格數字，不是所有音訊錄音通用的分鐘時長。檔案大小規則與 token 額度描述不同限制。較長素材應依文件記載的檔案流程準備錄音，在各部分間傳遞相關脈絡，並確認最終文字包含來源結尾。

有用的 Mini Transcribe 結果會保留用字及其與錄音的關係，並將可選機率資料與編輯修正分開。保留原始音訊，檢查不熟悉的詞彙、口音、背景雜音、語言變換及重疊發言。為提升可讀性而修改文字時，應將編輯版本與辨識逐字稿分開，讓後續使用者能辨別哪些用字來自錄音，哪些在準備過程中被修改。

", "aboutText": "GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它接受音訊及可選的文字引導，產生辨識文字。它與使用 GPT-4o 的 GPT-4o Transcribe，以及具有獨立關鍵字與多語言提示欄位、較新的 GPT Transcribe 設定檔，是不同模型。這裡有用的成品是錄音原始發言的逐字稿，可用於搜尋、檢閱或後續內容處理步驟。\n\n### 準備錄音\n\nOpenAI 的檔案轉錄指南接受最多 25 MB 的音訊上傳。目前的端點參考列出 FLAC、MP3、MP4、MPEG、MPGA、M4A、OGG、WAV 與 WebM，並要求足夠的檔名與內容類型中繼資料，以識別音訊格式。較大的錄音可壓縮或分成每個不超過 25 MB 的部分。分割時保留句子邊界，並讓各部分連到來源錄音與位置，以便之後依正確順序組合文字。\n\n語音筆記應為每份錄音保留一份可識別的逐字稿，並在用文字建立任務前確認名稱或數字。口述教學應在為發布而編輯前，先將辨識用字與原始指示對照。有用的準備說明會指出發言語言及可能聽錯的術語。轉錄字句是第一步；之後可用檢查過的逐字稿進行解讀、摘要或翻譯。\n\n### 提示詞引導與單一語言提示\n\n既有 GPT-4o Mini Transcribe 整合支援自由形式提示詞。OpenAI 描述可用提示詞提供名稱、縮寫、錄音專用詞彙、標點、大小寫、語助填充詞及偏好的書寫系統。端點參考表示提示詞應符合音訊語言，並可攜帶前一音訊片段的脈絡。加入相關拼法或簡短主題說明，不要要求轉錄提示詞像不受限制的聊天指示一樣運作。\n\n這個模型既有的語言提示使用單數 language 欄位。開發商參考文件記載 ISO 639-1 輸入語言代碼，例如 en。獨立的 keywords 與複數 languages 欄位是 GPT Transcribe 的文件內容，並非這個 Mini 設定檔的一部分。多份錄音應讓各輸入保留預定的發言語言設定，不要將其解讀成翻譯結果的請求。\n\n### JSON 結果與可選 token 機率\n\n目前的端點參考將 JSON 記為 GPT-4o Mini Transcribe 支援的回應格式。辨識用字顯示於 text 欄位。要求時，JSON 回應可附帶 token 對數機率；這些值描述模型的 token 機率，並可協助找出需要仔細檢閱的素材。它們無法證明名稱、數字或句子符合聲音。應依錄音判斷可疑字詞是否需要修正。\n\n一般 Mini 轉錄設定檔不會透過這個 JSON 規格提供原生 SRT、VTT、詳細逐字時間戳或附說話者標籤的輸出。OpenAI 為這些能力記載了專用模型與格式。若預定成品是字幕軌，應保留檢閱過的逐字稿，供獨立時間標記流程使用，不要假設純文字結果已包含字幕邊界。\n\n### 檔案輸出串流與文件記載模式\n\n開發商的語音轉文字指南明確表示，既有 GPT-4o Mini Transcribe 整合支援檔案串流。已完成錄音可在處理時先產生部分逐字稿文字，再產生最終結果。將最終逐字稿保留為完成成品；出現部分文字不代表檔案流程正在持續接收即時麥克風音訊。模型卡另列轉錄與 Realtime 端點家族。這些開發商介面不代表其他轉錄模型的所有工作階段欄位都適用於此。\n\n### 上下文、輸出額度與實用檢查\n\nOpenAI 目前的模型規格列出 16,000 個 token 的上下文視窗、2,000 個 token 的最大輸出，以及 2024 年 6 月 1 日的知識截止日。這些是模型規格數字，不是所有音訊錄音通用的分鐘時長。檔案大小規則與 token 額度描述不同限制。較長素材應依文件記載的檔案流程準備錄音，在各部分間傳遞相關脈絡，並確認最終文字包含來源結尾。\n\n有用的 Mini Transcribe 結果會保留用字及其與錄音的關係，並將可選機率資料與編輯修正分開。保留原始音訊，檢查不熟悉的詞彙、口音、背景雜音、語言變換及重疊發言。為提升可讀性而修改文字時，應將編輯版本與辨識逐字稿分開，讓後續使用者能辨別哪些用字來自錄音，哪些在準備過程中被修改。", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "4b10c1d6391a9117d26beefb75582f4956546c706780e8f714fcdec160ebfff7", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "zh-hant-tw", "methods": [ { "html": "
O

OpenAI: GPT-4o Mini Transcribe

OpenAI /openai/gpt-4o-mini-transcribe

入門

GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它將音訊轉成 JSON 逐字稿，支援錄音專用文字提示詞與檔案結果串流，也可回傳 token 對數機率，供針對性的逐字稿檢閱使用。

接受的輸入
音訊
結果
文字
關於模型

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。

GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它接受音訊及可選的文字引導，產生辨識文字。它與使用 GPT-4o 的 GPT-4o Transcribe，以及具有獨立關鍵字與多語言提示欄位、較新的 GPT Transcribe 設定檔，是不同模型。這裡有用的成品是錄音原始發言的逐字稿，可用於搜尋、檢閱或後續內容處理步驟。

準備錄音

OpenAI 的檔案轉錄指南接受最多 25 MB 的音訊上傳。目前的端點參考列出 FLAC、MP3、MP4、MPEG、MPGA、M4A、OGG、WAV 與 WebM，並要求足夠的檔名與內容類型中繼資料，以識別音訊格式。較大的錄音可壓縮或分成每個不超過 25 MB 的部分。分割時保留句子邊界，並讓各部分連到來源錄音與位置，以便之後依正確順序組合文字。

語音筆記應為每份錄音保留一份可識別的逐字稿，並在用文字建立任務前確認名稱或數字。口述教學應在為發布而編輯前，先將辨識用字與原始指示對照。有用的準備說明會指出發言語言及可能聽錯的術語。轉錄字句是第一步；之後可用檢查過的逐字稿進行解讀、摘要或翻譯。

提示詞引導與單一語言提示

既有 GPT-4o Mini Transcribe 整合支援自由形式提示詞。OpenAI 描述可用提示詞提供名稱、縮寫、錄音專用詞彙、標點、大小寫、語助填充詞及偏好的書寫系統。端點參考表示提示詞應符合音訊語言，並可攜帶前一音訊片段的脈絡。加入相關拼法或簡短主題說明，不要要求轉錄提示詞像不受限制的聊天指示一樣運作。

這個模型既有的語言提示使用單數 language 欄位。開發商參考文件記載 ISO 639-1 輸入語言代碼，例如 en。獨立的 keywords 與複數 languages 欄位是 GPT Transcribe 的文件內容，並非這個 Mini 設定檔的一部分。多份錄音應讓各輸入保留預定的發言語言設定，不要將其解讀成翻譯結果的請求。

JSON 結果與可選 token 機率

目前的端點參考將 JSON 記為 GPT-4o Mini Transcribe 支援的回應格式。辨識用字顯示於 text 欄位。要求時，JSON 回應可附帶 token 對數機率；這些值描述模型的 token 機率，並可協助找出需要仔細檢閱的素材。它們無法證明名稱、數字或句子符合聲音。應依錄音判斷可疑字詞是否需要修正。

一般 Mini 轉錄設定檔不會透過這個 JSON 規格提供原生 SRT、VTT、詳細逐字時間戳或附說話者標籤的輸出。OpenAI 為這些能力記載了專用模型與格式。若預定成品是字幕軌，應保留檢閱過的逐字稿，供獨立時間標記流程使用，不要假設純文字結果已包含字幕邊界。

檔案輸出串流與文件記載模式

開發商的語音轉文字指南明確表示，既有 GPT-4o Mini Transcribe 整合支援檔案串流。已完成錄音可在處理時先產生部分逐字稿文字，再產生最終結果。將最終逐字稿保留為完成成品；出現部分文字不代表檔案流程正在持續接收即時麥克風音訊。模型卡另列轉錄與 Realtime 端點家族。這些開發商介面不代表其他轉錄模型的所有工作階段欄位都適用於此。

上下文、輸出額度與實用檢查

OpenAI 目前的模型規格列出 16,000 個 token 的上下文視窗、2,000 個 token 的最大輸出，以及 2024 年 6 月 1 日的知識截止日。這些是模型規格數字，不是所有音訊錄音通用的分鐘時長。檔案大小規則與 token 額度描述不同限制。較長素材應依文件記載的檔案流程準備錄音，在各部分間傳遞相關脈絡，並確認最終文字包含來源結尾。

有用的 Mini Transcribe 結果會保留用字及其與錄音的關係，並將可選機率資料與編輯修正分開。保留原始音訊，檢查不熟悉的詞彙、口音、背景雜音、語言變換及重疊發言。為提升可讀性而修改文字時，應將編輯版本與辨識逐字稿分開，讓後續使用者能辨別哪些用字來自錄音，哪些在準備過程中被修改。

Ailoot 可用 · 輸入與方法

Ailoot Ultra · 語音轉文字 POST /v1/audio/transcriptions
輸入
audio
輸出
text
欄位類型要求值與限制預設值
欄位model類型string要求必填值與限制
openai/gpt-4o-mini-transcribe
預設值—
欄位input_audio類型object要求必填值與限制預設值—
方法參數與生命週期
參數規格
參數content_type規格application/json
參數required規格model, input_audio
參數material_types規格audio
參數material_conditions規格此範例會讀取您實際使用且非空的 PCM WAV 檔案，將完整檔案位元組編碼為 base64，並將 input_audio.format 設為 wav 傳送。

生命週期： synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · 現有自有媒體紀錄中完全相符的 task_id

GET /v1/media/assets/{asset_id}/content

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

方案

費率資訊不會增加請求選項。支援的參數列於所選方法中。

快速模式
未指定 選取快速模式時
flex 模式
未指定 選取 flex 模式時
最高推理強度
未指定 最高推理強度採用 default 調整值時

Ailoot 費率

各設定的價格

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。

設定費率表計費單位費用
設定基礎 token 費率費率表基本費率計費單位—費用
輸入 · 輸入 Token — / 1K Token
輸出 · 輸出 Token — / 1K Token
輸入 · 讀取快取 — / 1K Token
輸入 · 寫入快取 — / 1K Token
輸入 · 寫入快取，1 小時 — / 1K Token
設定輸入 token費率表—計費單位/ 1K Token費用
輸入 $0.0025 / 1K Token
設定輸出 token費率表—計費單位/ 1K Token費用
輸出 $0.01 / 1K Token

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。預留金額與結算的運作方式 →

請求範例

Ailoot Ultra · 語音轉文字

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set the path to your actual PCM WAV recording}"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport base64, io, json, os, wave\nfrom pathlib import Path\naudio = Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4] == b'RIFF' and audio[8:12] == b'WAVE'):\n    raise SystemExit('Supply your actual PCM WAV audio file')\nwith wave.open(io.BytesIO(audio), 'rb') as recording:\n    if recording.getcomptype() != 'NONE' or recording.getnframes() <= 0:\n        raise SystemExit('Supply a nonempty PCM WAV recording')\nrequest = {'model': 'openai/gpt-4o-mini-transcribe', 'input_audio': {'data': base64.b64encode(audio).decode('ascii'), 'format': 'wav'}}\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# Retain the complete original response, headers and actual X-Client-Request-ID.\n# Read existing owned records for recovery; do not resubmit an uncertain operation.\n

接收並儲存結果

Ailoot Ultra · 語音轉文字

完整的原始回應本文、狀態與轉送標頭。此處理常式不會加入通用的 JSON 結構、文字欄位或工作封裝。

保留所有已完成的結果

請保留所有完整傳回的回應、檔案與內容區塊。

保留完整回應與標頭、所有實際輸出、原始回傳的識別碼，以及所有用量欄位。恢復原始作業時，請勿再次提交建立請求。

需要檢查原始回應時

請保留實際的 X-Client-Request-ID 與完整回應。請讀取原始自有資產及其完全相符的簽署內容 URL；切勿重新提交結果不明的建立請求。

回應欄位
欄位類型
欄位text (when present)類型
欄位usage (when present)類型
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件JSON 本文或明確的標準模型 ID 無效。下一步請保留回應，並修正指出的請求欄位。
回應401 · authentication_error條件Ailoot API 金鑰無效。下一步請使用您已獲授權的 Ailoot API 金鑰。
回應403 · permission_error條件此金鑰群組未獲准使用該方法。下一步請保留回傳的錯誤詳細資訊。
回應404 · not_found_error條件所選方法沒有獲准使用的路由。下一步請保留回傳的錯誤詳細資訊。
回應422 · price_unavailable條件已接受的費率無法取得其所需的輸入數量或界限。下一步請保留回應，並使用已接受費率所要求的輸入表示方式。
回應503 · 條件所需的儲存系統、路由、方法價格或預留額度無法使用。下一步請保留完整的原始回應。預留額度狀態不明並不代表可以重新提交。
回應502 · server_error條件原始結果、用量或結算需要查核。下一步請保留實際的請求 ID 與原始回應。請讀取現有的自有紀錄，切勿重新提交建立請求。

別名

模型別名

Ailoot Ultra openai/gpt-4o-mini-transcribe

方法路徑別名

請使用上方列出的 API 方法路徑。

相關呼叫用 ID

openai/gpt-4o-mini-transcribe

", "method_identity": { "effective_request_model_id": "openai/gpt-4o-mini-transcribe", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "openai/gpt-4o-mini-transcribe", "route_label": "Ultra" }, "method_key": "Ultra|transcriptions|/v1/audio/transcriptions|openai%2Fgpt-4o-mini-transcribe", "ordinal": 0, "rawMethod": { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "errors": [ { "code": null, "condition": "JSON 本文或明確的標準模型 ID 無效。", "http_status": 400, "recovery": "請保留回應，並修正指出的請求欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "Ailoot API 金鑰無效。", "http_status": 401, "recovery": "請使用您已獲授權的 Ailoot API 金鑰。", "type": "authentication_error" }, { "code": null, "condition": "此金鑰群組未獲准使用該方法。", "http_status": 403, "recovery": "請保留回傳的錯誤詳細資訊。", "type": "permission_error" }, { "code": null, "condition": "所選方法沒有獲准使用的路由。", "http_status": 404, "recovery": "請保留回傳的錯誤詳細資訊。", "type": "not_found_error" }, { "code": null, "condition": "已接受的費率無法取得其所需的輸入數量或界限。", "http_status": 422, "recovery": "請保留回應，並使用已接受費率所要求的輸入表示方式。", "type": "price_unavailable" }, { "code": null, "condition": "所需的儲存系統、路由、方法價格或預留額度無法使用。", "http_status": 503, "recovery": "請保留完整的原始回應。預留額度狀態不明並不代表可以重新提交。", "type": null }, { "code": null, "condition": "原始結果、用量或結算需要查核。", "http_status": 502, "operation_id_source": "actual X-Client-Request-ID", "recovery": "請保留實際的請求 ID 與原始回應。請讀取現有的自有紀錄，切勿重新提交建立請求。", "response_headers": { "x-should-retry": "false" }, "type": "server_error" } ], "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "exact task_id from an existing owned media record", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "請保留實際的 X-Client-Request-ID 與完整回應。請讀取原始自有資產及其完全相符的簽署內容 URL；切勿重新提交結果不明的建立請求。" }, "outputs": { "all_results": "保留完整回應與標頭、所有實際輸出、原始回傳的識別碼，以及所有用量欄位。恢復原始作業時，請勿再次提交建立請求。", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "完整的原始回應本文、狀態與轉送標頭。此處理常式不會加入通用的 JSON 結構、文字欄位或工作封裝。" }, "parameters": [ { "default_known": false, "enum": [ "openai/gpt-4o-mini-transcribe" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "name": "input_audio", "required": true, "type": "object" } ], "request_schema": { "properties": { "input_audio": { "properties": { "data": { "contentEncoding": "base64", "type": "string" }, "format": { "type": "string" } }, "required": [ "data", "format" ], "type": "object" }, "model": { "enum": [ "openai/gpt-4o-mini-transcribe" ], "type": "string" } }, "required": [ "model", "input_audio" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_audio": { "data": "${BASE64_ACTUAL_WAV_BYTES}", "format": "wav" }, "model": "openai/gpt-4o-mini-transcribe" }, "content_type": "application/json" } }, "input": { "content_type": "application/json", "material_conditions": [ "此範例會讀取您實際使用且非空的 PCM WAV 檔案，將完整檔案位元組編碼為 base64，並將 input_audio.format 設為 wav 傳送。" ], "material_types": [ "audio" ], "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "現有自有媒體紀錄中完全相符的 task_id", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Retain the actual X-Client-Request-ID and complete response. Read the original owned assets and their exact signed content URLs; never resubmit an uncertain creation." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "output": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "Complete original response body, status and forwarded headers. No universal JSON shape, text field or task envelope is added by this handler." } }, "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": { "quoted_unit": "/ 1K tokens" }, "label": "input token", "units": [ { "amount": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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" } ] }, { "dimensions": { "quoted_unit": "/ 1K tokens" }, "label": "output token", "units": [ { "amount": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual PCM WAV recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport base64, io, json, os, wave\nfrom pathlib import Path\naudio = Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4] == b'RIFF' and audio[8:12] == b'WAVE'):\n raise SystemExit('Supply your actual PCM WAV audio file')\nwith wave.open(io.BytesIO(audio), 'rb') as recording:\n if recording.getcomptype() != 'NONE' or recording.getnframes() <= 0:\n raise SystemExit('Supply a nonempty PCM WAV recording')\nrequest = {'model': 'openai/gpt-4o-mini-transcribe', 'input_audio': {'data': base64.b64encode(audio).decode('ascii'), 'format': 'wav'}}\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# Retain the complete original response, headers and actual X-Client-Request-ID.\n# Read existing owned records for recovery; do not resubmit an uncertain operation.\n", "label": "curl · actual WAV file and complete original result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "The example reads your actual nonempty PCM WAV file, encodes the complete file bytes as base64 and sends input_audio.format as wav.", "The format value in the example is the documented recipe; no model-specific format list, limit or default is asserted.", "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again." ], "http": "POST", "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "audio_transcriptions", "out": null, "output": [ "text" ], "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": { "input_token": 2.5e-06, "output_token": 1e-05 } }, "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": { "quoted_unit": "/ 1K tokens" }, "label": "input token", "units": [ { "amount": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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" } ] }, { "dimensions": { "quoted_unit": "/ 1K tokens" }, "label": "output token", "units": [ { "amount": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ] } ], "request_model_id": "openai/gpt-4o-mini-transcribe", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "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": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ] } } ], "model_id": "openai/gpt-4o-mini-transcribe", "nativeProvenance": { "input_facts_canonical_sha256": "376848cbc487070f4df1b4508518b68bd80643572d3290e08cb19133f5dcd34b", "input_html_sha256": "939c78b7b0949579fa4c5a108d33ab141f43106e1c2b50890f0a9bb89cad08c1", "private_audit_sha256": "6bdf31210cd03a579b9e32633e6a803930f275df2cf2cce1ac69348e83ef6540", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/zh-hant-tw/openai-gpt-4o-mini-transcribe/", "description": "GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它將音訊轉成 JSON 逐字稿，支援錄音專用文字提示詞與檔案結果串流，也可回傳 token 對數機率，供針對性的逐字稿檢閱使用。", "locale": "zh-hant-tw", "md_url": "https://ailoot.ai/models/zh-hant-tw/openai-gpt-4o-mini-transcribe/index.md", "title": "OpenAI: GPT-4o Mini Transcribe — Ailoot", "url": "https://ailoot.ai/models/zh-hant-tw/openai-gpt-4o-mini-transcribe/" }, "rawModel": { "about": "GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它接受音訊及可選的文字引導，產生辨識文字。它與使用 GPT-4o 的 GPT-4o Transcribe，以及具有獨立關鍵字與多語言提示欄位、較新的 GPT Transcribe 設定檔，是不同模型。這裡有用的成品是錄音原始發言的逐字稿，可用於搜尋、檢閱或後續內容處理步驟。\n\n### 準備錄音\n\nOpenAI 的檔案轉錄指南接受最多 25 MB 的音訊上傳。目前的端點參考列出 FLAC、MP3、MP4、MPEG、MPGA、M4A、OGG、WAV 與 WebM，並要求足夠的檔名與內容類型中繼資料，以識別音訊格式。較大的錄音可壓縮或分成每個不超過 25 MB 的部分。分割時保留句子邊界，並讓各部分連到來源錄音與位置，以便之後依正確順序組合文字。\n\n語音筆記應為每份錄音保留一份可識別的逐字稿，並在用文字建立任務前確認名稱或數字。口述教學應在為發布而編輯前，先將辨識用字與原始指示對照。有用的準備說明會指出發言語言及可能聽錯的術語。轉錄字句是第一步；之後可用檢查過的逐字稿進行解讀、摘要或翻譯。\n\n### 提示詞引導與單一語言提示\n\n既有 GPT-4o Mini Transcribe 整合支援自由形式提示詞。OpenAI 描述可用提示詞提供名稱、縮寫、錄音專用詞彙、標點、大小寫、語助填充詞及偏好的書寫系統。端點參考表示提示詞應符合音訊語言，並可攜帶前一音訊片段的脈絡。加入相關拼法或簡短主題說明，不要要求轉錄提示詞像不受限制的聊天指示一樣運作。\n\n這個模型既有的語言提示使用單數 language 欄位。開發商參考文件記載 ISO 639-1 輸入語言代碼，例如 en。獨立的 keywords 與複數 languages 欄位是 GPT Transcribe 的文件內容，並非這個 Mini 設定檔的一部分。多份錄音應讓各輸入保留預定的發言語言設定，不要將其解讀成翻譯結果的請求。\n\n### JSON 結果與可選 token 機率\n\n目前的端點參考將 JSON 記為 GPT-4o Mini Transcribe 支援的回應格式。辨識用字顯示於 text 欄位。要求時，JSON 回應可附帶 token 對數機率；這些值描述模型的 token 機率，並可協助找出需要仔細檢閱的素材。它們無法證明名稱、數字或句子符合聲音。應依錄音判斷可疑字詞是否需要修正。\n\n一般 Mini 轉錄設定檔不會透過這個 JSON 規格提供原生 SRT、VTT、詳細逐字時間戳或附說話者標籤的輸出。OpenAI 為這些能力記載了專用模型與格式。若預定成品是字幕軌，應保留檢閱過的逐字稿，供獨立時間標記流程使用，不要假設純文字結果已包含字幕邊界。\n\n### 檔案輸出串流與文件記載模式\n\n開發商的語音轉文字指南明確表示，既有 GPT-4o Mini Transcribe 整合支援檔案串流。已完成錄音可在處理時先產生部分逐字稿文字，再產生最終結果。將最終逐字稿保留為完成成品；出現部分文字不代表檔案流程正在持續接收即時麥克風音訊。模型卡另列轉錄與 Realtime 端點家族。這些開發商介面不代表其他轉錄模型的所有工作階段欄位都適用於此。\n\n### 上下文、輸出額度與實用檢查\n\nOpenAI 目前的模型規格列出 16,000 個 token 的上下文視窗、2,000 個 token 的最大輸出，以及 2024 年 6 月 1 日的知識截止日。這些是模型規格數字，不是所有音訊錄音通用的分鐘時長。檔案大小規則與 token 額度描述不同限制。較長素材應依文件記載的檔案流程準備錄音，在各部分間傳遞相關脈絡，並確認最終文字包含來源結尾。\n\n有用的 Mini Transcribe 結果會保留用字及其與錄音的關係，並將可選機率資料與編輯修正分開。保留原始音訊，檢查不熟悉的詞彙、口音、背景雜音、語言變換及重疊發言。為提升可讀性而修改文字時，應將編輯版本與辨識逐字稿分開，讓後續使用者能辨別哪些用字來自錄音，哪些在準備過程中被修改。", "alias_of": null, "aliases": [], "author": "OpenAI", "capabilities": { "context_length": 128000, "manufacturer_input": [ "audio" ], "manufacturer_output": [ "transcription" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ], "summary": "完整的設定價格資訊請見詳細資料。" } ], "ctx": null, "formats": [ "transcriptions" ], "id": "openai/gpt-4o-mini-transcribe", "input": [ "audio" ], "kind": "audio", "max_out": null, "methods": [ { "available": null, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "errors": [ { "code": null, "condition": "JSON 本文或明確的標準模型 ID 無效。", "http_status": 400, "recovery": "請保留回應，並修正指出的請求欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "Ailoot API 金鑰無效。", "http_status": 401, "recovery": "請使用您已獲授權的 Ailoot API 金鑰。", "type": "authentication_error" }, { "code": null, "condition": "此金鑰群組未獲准使用該方法。", "http_status": 403, "recovery": "請保留回傳的錯誤詳細資訊。", "type": "permission_error" }, { "code": null, "condition": "所選方法沒有獲准使用的路由。", "http_status": 404, "recovery": "請保留回傳的錯誤詳細資訊。", "type": "not_found_error" }, { "code": null, "condition": "已接受的費率無法取得其所需的輸入數量或界限。", "http_status": 422, "recovery": "請保留回應，並使用已接受費率所要求的輸入表示方式。", "type": "price_unavailable" }, { "code": null, "condition": "所需的儲存系統、路由、方法價格或預留額度無法使用。", "http_status": 503, "recovery": "請保留完整的原始回應。預留額度狀態不明並不代表可以重新提交。", "type": null }, { "code": null, "condition": "原始結果、用量或結算需要查核。", "http_status": 502, "operation_id_source": "actual X-Client-Request-ID", "recovery": "請保留實際的請求 ID 與原始回應。請讀取現有的自有紀錄，切勿重新提交建立請求。", "response_headers": { "x-should-retry": "false" }, "type": "server_error" } ], "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "exact task_id from an existing owned media record", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "請保留實際的 X-Client-Request-ID 與完整回應。請讀取原始自有資產及其完全相符的簽署內容 URL；切勿重新提交結果不明的建立請求。" }, "outputs": { "all_results": "保留完整回應與標頭、所有實際輸出、原始回傳的識別碼，以及所有用量欄位。恢復原始作業時，請勿再次提交建立請求。", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "完整的原始回應本文、狀態與轉送標頭。此處理常式不會加入通用的 JSON 結構、文字欄位或工作封裝。" }, "parameters": [ { "default_known": false, "enum": [ "openai/gpt-4o-mini-transcribe" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "default_known": false, "enum_known": false, "name": "input_audio", "required": true, "type": "object" } ], "request_schema": { "properties": { "input_audio": { "properties": { "data": { "contentEncoding": "base64", "type": "string" }, "format": { "type": "string" } }, "required": [ "data", "format" ], "type": "object" }, "model": { "enum": [ "openai/gpt-4o-mini-transcribe" ], "type": "string" } }, "required": [ "model", "input_audio" ], "type": "object" }, "schema_template": { "actual_file_preparation_required": true, "body": { "input_audio": { "data": "${BASE64_ACTUAL_WAV_BYTES}", "format": "wav" }, "model": "openai/gpt-4o-mini-transcribe" }, "content_type": "application/json" } }, "input": { "content_type": "application/json", "material_conditions": [ "此範例會讀取您實際使用且非空的 PCM WAV 檔案，將完整檔案位元組編碼為 base64，並將 input_audio.format 設為 wav 傳送。" ], "material_types": [ "audio" ], "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 content URL" } ], "dedicated_method_polling_or_cancel": false, "mode": "synchronous_result_then_owned_library", "original_POST_adds_task_envelope": false, "status": [ { "http": "GET", "id_source": "現有自有媒體紀錄中完全相符的 task_id", "path": "/v1/media/tasks/{task_id}" } ], "unknown": "Retain the actual X-Client-Request-ID and complete response. Read the original owned assets and their exact signed content URLs; never resubmit an uncertain creation." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "output": { "all_results": "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again.", "family": "text", "fields": [ { "description": null, "name": "text (when present)", "type": null }, { "description": null, "name": "usage (when present)", "type": null } ], "result": "Complete original response body, status and forwarded headers. No universal JSON shape, text field or task envelope is added by this handler." } }, "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": { "quoted_unit": "/ 1K tokens" }, "label": "input token", "units": [ { "amount": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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" } ] }, { "dimensions": { "quoted_unit": "/ 1K tokens" }, "label": "output token", "units": [ { "amount": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ] } ], "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set the path to your actual PCM WAV recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport base64, io, json, os, wave\nfrom pathlib import Path\naudio = Path(os.environ['AILOOT_AUDIO_FILE']).read_bytes()\nif not (audio[:4] == b'RIFF' and audio[8:12] == b'WAVE'):\n raise SystemExit('Supply your actual PCM WAV audio file')\nwith wave.open(io.BytesIO(audio), 'rb') as recording:\n if recording.getcomptype() != 'NONE' or recording.getnframes() <= 0:\n raise SystemExit('Supply a nonempty PCM WAV recording')\nrequest = {'model': 'openai/gpt-4o-mini-transcribe', 'input_audio': {'data': base64.b64encode(audio).decode('ascii'), 'format': 'wav'}}\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# Retain the complete original response, headers and actual X-Client-Request-ID.\n# Read existing owned records for recovery; do not resubmit an uncertain operation.\n", "label": "curl · actual WAV file and complete original result", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "hints": [ "The example reads your actual nonempty PCM WAV file, encodes the complete file bytes as base64 and sends input_audio.format as wav.", "The format value in the example is the documented recipe; no model-specific format list, limit or default is asserted.", "Retain the complete response and headers, every actual output, original returned identifiers and all usage fields. Recover the original operation without submitting creation again." ], "http": "POST", "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "native_endpoint": "audio_transcriptions", "out": null, "output": [ "text" ], "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": { "input_token": 2.5e-06, "output_token": 1e-05 } }, "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": { "quoted_unit": "/ 1K tokens" }, "label": "input token", "units": [ { "amount": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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" } ] }, { "dimensions": { "quoted_unit": "/ 1K tokens" }, "label": "output token", "units": [ { "amount": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ] } ], "request_model_id": "openai/gpt-4o-mini-transcribe", "route_label": "Ultra", "status_reads": [ "GET /v1/media/tasks/{task_id}" ], "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": "0.0025000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "input_token", "label": "input token", "native_amount_usd_per_unit": "0.0000025", "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": "0.01000", "amount_unit": "usd_per_thousand_tokens", "billing_input": true, "estimate_only": false, "key": "output_token", "label": "output token", "native_amount_usd_per_unit": "0.00001", "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" } ] } ], "model_aliases": [ { "canonical_model_id": "openai/gpt-4o-mini-transcribe", "request_model_id": "openai/gpt-4o-mini-transcribe", "route_label": "Ultra" } ], "name": "OpenAI: GPT-4o Mini Transcribe", "price": { "in": null, "in_label": null, "out": 0.01, "out_label": "/ 1K tokens", "sort_in": null, "sort_out": 0.01, "varies": true }, "short": "GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它將音訊轉成 JSON 逐字稿，支援錄音專用文字提示詞與檔案結果串流，也可回傳 token 對數機率，供針對性的逐字稿檢閱使用。" }, "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": "GPT-4o Mini Transcribe 是 OpenAI 以 GPT-4o Mini 為基礎的語音轉文字模型。它將音訊轉成 JSON 逐字稿，支援錄音專用文字提示詞與檔案結果串流，也可回傳 token 對數機率，供針對性的逐字稿檢閱使用。", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "626efc9c7bae1b00394f874f8a5630dde51b0061b5156c77b4c513d70220f37e", "renderer_sha256": "13a3fc1b22d07359278e2249d630bfc9bb9e6416c71ba53def933fb5a903660b" }, "sourceRevision": "5a1bf2287872f7fbd61e3214fda1bba42bb49ed677ab7770d466283195aa16da" }