{ "aboutHtml": "

Qwen-Audio-3.0-ASR-Flash 用於將語音錄音轉成文字。Alibaba 著重多語言辨識及富有表現力的語音，包括詩歌節奏、文言文與文化敘事。輸入為音訊，結果為轉錄文字。

將語音寫成文字

模型會加入標點，並將口述數字、日期及金額轉成通用的書寫形式。適合語音訊息、訪談片段及教學語音，這些用途需要易讀文字，而不只是辨識出的詞語序列。

支援 30 種語言，包括俄語、英語、法語、德語、日語及阿拉伯語。另外涵蓋七大漢語方言系統，以及超過 20 種地區發音變體。此範圍用於辨識不同語言與口音的特徵。

針對專門術語，可提供任務背景及提示詞，協助引導人名與領域用語的辨識。此版本的時間戳記始終啟用，可將結果連結到錄音中的對應片段。短檔案的轉錄文字可一次完整回傳，也可隨處理進度逐步回傳。

素材與限制

錄音長度上限為五分鐘。每項任務使用一個檔案。支援 AAC、AMR、AVI、FLAC、FLV、M4A、MKV、MOV、MP3、MP4、MPEG、OGG、OPUS、WAV、WEBM、WMA 及 WMV；可使用任何取樣率。格式清單包含影片容器，是為了從其中的聲音部分擷取語音，不代表會對影格進行視覺分析。

Qwen-Audio-3.0-ASR-Flash 不支援依說話者區分內容或辨識情緒。主要結果是文字，以及辨識內容與錄音時間的對應關係。其他鄰近模型宣稱的較長錄音處理能力及其他音訊分析方式，不適用於此版本。

", "aboutText": "Qwen-Audio-3.0-ASR-Flash 用於將語音錄音轉成文字。Alibaba 著重多語言辨識及富有表現力的語音，包括詩歌節奏、文言文與文化敘事。輸入為音訊，結果為轉錄文字。\n\n### 將語音寫成文字\n\n模型會加入標點，並將口述數字、日期及金額轉成通用的書寫形式。適合語音訊息、訪談片段及教學語音，這些用途需要易讀文字，而不只是辨識出的詞語序列。\n\n支援 30 種語言，包括俄語、英語、法語、德語、日語及阿拉伯語。另外涵蓋七大漢語方言系統，以及超過 20 種地區發音變體。此範圍用於辨識不同語言與口音的特徵。\n\n針對專門術語，可提供任務背景及提示詞，協助引導人名與領域用語的辨識。此版本的時間戳記始終啟用，可將結果連結到錄音中的對應片段。短檔案的轉錄文字可一次完整回傳，也可隨處理進度逐步回傳。\n\n### 素材與限制\n\n錄音長度上限為五分鐘。每項任務使用一個檔案。支援 AAC、AMR、AVI、FLAC、FLV、M4A、MKV、MOV、MP3、MP4、MPEG、OGG、OPUS、WAV、WEBM、WMA 及 WMV；可使用任何取樣率。格式清單包含影片容器，是為了從其中的聲音部分擷取語音，不代表會對影格進行視覺分析。\n\nQwen-Audio-3.0-ASR-Flash 不支援依說話者區分內容或辨識情緒。主要結果是文字，以及辨識內容與錄音時間的對應關係。其他鄰近模型宣稱的較長錄音處理能力及其他音訊分析方式，不適用於此版本。", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "22994890cfe8d682e2531d0b8c1b071552bcf7ec871c0ea9a38a1fdba5909907", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "zh-hant-tw", "methods": [ { "html": "
Al

qwen-audio-3.0-asr-flash

Alibaba /qwen-audio-3.0-asr-flash

入門

將音訊轉成易讀文字的語音辨識模型，會加入標點並將數字正規化。支援俄語及其他語言，也支援漢語方言。

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。

Qwen-Audio-3.0-ASR-Flash 用於將語音錄音轉成文字。Alibaba 著重多語言辨識及富有表現力的語音，包括詩歌節奏、文言文與文化敘事。輸入為音訊，結果為轉錄文字。

將語音寫成文字

模型會加入標點，並將口述數字、日期及金額轉成通用的書寫形式。適合語音訊息、訪談片段及教學語音，這些用途需要易讀文字，而不只是辨識出的詞語序列。

支援 30 種語言，包括俄語、英語、法語、德語、日語及阿拉伯語。另外涵蓋七大漢語方言系統，以及超過 20 種地區發音變體。此範圍用於辨識不同語言與口音的特徵。

針對專門術語，可提供任務背景及提示詞，協助引導人名與領域用語的辨識。此版本的時間戳記始終啟用，可將結果連結到錄音中的對應片段。短檔案的轉錄文字可一次完整回傳，也可隨處理進度逐步回傳。

素材與限制

錄音長度上限為五分鐘。每項任務使用一個檔案。支援 AAC、AMR、AVI、FLAC、FLV、M4A、MKV、MOV、MP3、MP4、MPEG、OGG、OPUS、WAV、WEBM、WMA 及 WMV；可使用任何取樣率。格式清單包含影片容器，是為了從其中的聲音部分擷取語音，不代表會對影格進行視覺分析。

Qwen-Audio-3.0-ASR-Flash 不支援依說話者區分內容或辨識情緒。主要結果是文字，以及辨識內容與錄音時間的對應關係。其他鄰近模型宣稱的較長錄音處理能力及其他音訊分析方式，不適用於此版本。

Ailoot 可用 · 輸入與方法

Ailoot · 語音轉文字 POST /v1/audio/transcriptions
輸入
audio
輸出
text
輸出格式
json
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
qwen-audio-3.0-asr-flash
預設值—
欄位file類型file要求必填值與限制
位元組數上限: 10,485,760
檔案格式: wav, mp3, m4a, ogg, webm, flac
內容類型: multipart/form-data
時長上限（秒）: 300
預設值—
欄位response_format類型string要求選填值與限制
json
預設值—
輸入素材組合

speech_to_text · 必填： actual audio file

方法參數與生命週期
參數規格
參數material_types規格audio
參數required規格null
參數optional_controls規格null

生命週期： synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · 實際回傳的 task_id 或媒體庫紀錄

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

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot 語音轉文字POST /v1/audio/transcriptions
輸入
US$0.0021 每分鐘音訊

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 · 語音轉文字

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ["AILOOT_AUDIO_FILE"])\nif not f.is_file() or f.suffix.lower()!=".mp3":raise SystemExit("Choose your actual MP3 recording")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" \\\n  --form-string model=qwen-audio-3.0-asr-flash -F "file=@$AILOOT_AUDIO_FILE" \\\n  -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n

接收並儲存結果

Ailoot · 語音轉文字

json

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。

請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。

需要檢查原始回應時

保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。

回應欄位
欄位類型
欄位text類型string
欄位segments[]類型object
欄位task_id類型string
欄位asset_url類型string
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。
回應server_error條件回傳的回應表示該作業或結果需要檢查下一步保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。

別名

模型別名

Ailoot qwen-audio-3.0-asr-flash, qwen-asr, qwen-asr-latest

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

qwen-audio-3.0-asr-flash, qwen-asr, qwen-asr-latest

", "method_identity": { "effective_request_model_id": "qwen-audio-3.0-asr-flash", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "qwen-audio-3.0-asr-flash", "route_label": "Core" }, "method_key": "Core|transcriptions|/v1/audio/transcriptions|qwen-audio-3.0-asr-flash", "ordinal": 0, "rawMethod": { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "回傳的回應表示該作業或結果需要檢查", "http_status": null, "recovery": "保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。", "type": "server_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.", "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": "保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。" }, "material_combinations": [ { "content_type": "multipart/form-data", "mode": "speech_to_text", "required": [ "actual audio file" ] } ], "media_library": { "asset": { "fields": [ { "description": null, "name": "asset_id", "type": "string" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "output_key", "type": "string" }, { "description": null, "name": "family", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "method", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "content_type", "type": "string" }, { "description": null, "name": "sha256", "type": "string" }, { "description": null, "name": "size_bytes", "type": "integer" }, { "description": null, "name": "content_url", "type": "string" } ], "http": "GET", "id_source": "actual returned asset_id", "path": "/v1/media/assets/{asset_id}" }, "content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "range_header_supported": true, "url_source": "Use exact returned signed content_url including its token; do not construct a token." }, "expired_link": { "code": "link_expired", "http_status": 404, "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate." }, "list": { "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.", "http": "GET", "output_fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "data", "type": "asset[]" }, { "description": null, "name": "next_cursor", "type": "string|null" } ], "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "family", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "cursor", "required": false, "type": "string" }, { "availability": "source_interface", "default": 20, "default_known": true, "enum": null, "enum_known": false, "maximum": 100, "minimum": 1, "name": "limit", "required": false, "type": "integer" } ], "path": "/v1/media/assets" }, "revoke": { "http": "DELETE", "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.", "path": "/v1/media/assets/{asset_id}", "pending_status": "revoking", "success_statuses": [ 202, 204 ] }, "task": { "http": "GET", "id_source": "actual returned task_id or media library record; operation_id is not task_id", "path": "/v1/media/tasks/{task_id}" } }, "operation_modes": [ "speech_to_text" ], "outputs": { "all_results": "請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。", "family": "transcription", "fields": [ { "description": null, "name": "text", "type": "string" }, { "description": null, "name": "segments[]", "type": "object" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "asset_url", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "qwen-audio-3.0-asr-flash" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "content_type": "multipart/form-data", "default": null, "default_known": false, "enum": null, "enum_known": false, "file_formats": [ "wav", "mp3", "m4a", "ogg", "webm", "flac" ], "maximum_bytes": 10485760, "maximum_seconds": 300, "name": "file", "required": true, "type": "file" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "material_types": [ "audio" ], "optional_controls": null, "required": null }, "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 for reconciliation without resubmission; no dedicated audio poll route." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "operation_modes": [ "audio_transcriptions" ], "output": { "family": [ "text" ], "format": null, "multioutputs": "retain every actual response output" } }, "ctx": null, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not f.is_file() or f.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose your actual MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n --form-string model=qwen-audio-3.0-asr-flash -F \"file=@$AILOOT_AUDIO_FILE\" \\\n -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Transcribe your actual recording", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_tool_calls": null, "out": null, "output": [ "text" ], "path": "/v1/audio/transcriptions", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.0021, "amount_unit": "usd_per_display_unit", "key": "audio_input_second", "label": "per minute of audio", "side": "in" } ] } ], "request_model_id": "qwen-audio-3.0-asr-flash", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "audio_input_second", "units": [ { "key": "audio_input_second", "label": "per minute of audio", "side": "in", "usd": 0.0021 } ] } }, { "html": "
Al

qwen-audio-3.0-asr-flash

Alibaba /qwen-asr

入門

將音訊轉成易讀文字的語音辨識模型，會加入標點並將數字正規化。支援俄語及其他語言，也支援漢語方言。

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。

Qwen-Audio-3.0-ASR-Flash 用於將語音錄音轉成文字。Alibaba 著重多語言辨識及富有表現力的語音，包括詩歌節奏、文言文與文化敘事。輸入為音訊，結果為轉錄文字。

將語音寫成文字

模型會加入標點，並將口述數字、日期及金額轉成通用的書寫形式。適合語音訊息、訪談片段及教學語音，這些用途需要易讀文字，而不只是辨識出的詞語序列。

支援 30 種語言，包括俄語、英語、法語、德語、日語及阿拉伯語。另外涵蓋七大漢語方言系統，以及超過 20 種地區發音變體。此範圍用於辨識不同語言與口音的特徵。

針對專門術語，可提供任務背景及提示詞，協助引導人名與領域用語的辨識。此版本的時間戳記始終啟用，可將結果連結到錄音中的對應片段。短檔案的轉錄文字可一次完整回傳，也可隨處理進度逐步回傳。

素材與限制

錄音長度上限為五分鐘。每項任務使用一個檔案。支援 AAC、AMR、AVI、FLAC、FLV、M4A、MKV、MOV、MP3、MP4、MPEG、OGG、OPUS、WAV、WEBM、WMA 及 WMV；可使用任何取樣率。格式清單包含影片容器，是為了從其中的聲音部分擷取語音，不代表會對影格進行視覺分析。

Qwen-Audio-3.0-ASR-Flash 不支援依說話者區分內容或辨識情緒。主要結果是文字，以及辨識內容與錄音時間的對應關係。其他鄰近模型宣稱的較長錄音處理能力及其他音訊分析方式，不適用於此版本。

Ailoot 可用 · 輸入與方法

Ailoot · 語音轉文字 POST /v1/audio/transcriptions
輸入
audio
輸出
text
輸出格式
json
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
qwen-asr
預設值—
欄位file類型file要求必填值與限制
位元組數上限: 10,485,760
檔案格式: wav, mp3, m4a, ogg, webm, flac
內容類型: multipart/form-data
時長上限（秒）: 300
預設值—
欄位response_format類型string要求選填值與限制
json
預設值—
輸入素材組合

speech_to_text · 必填： actual audio file

方法參數與生命週期
參數規格
參數material_types規格audio
參數required規格null
參數optional_controls規格null

生命週期： synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · 實際回傳的 task_id 或媒體庫紀錄

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

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot 語音轉文字POST /v1/audio/transcriptions
輸入
US$0.0021 每分鐘音訊

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 · 語音轉文字

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ["AILOOT_AUDIO_FILE"])\nif not f.is_file() or f.suffix.lower()!=".mp3":raise SystemExit("Choose your actual MP3 recording")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" \\\n  --form-string model=qwen-asr -F "file=@$AILOOT_AUDIO_FILE" \\\n  -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n

接收並儲存結果

Ailoot · 語音轉文字

json

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。

請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。

需要檢查原始回應時

保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。

回應欄位
欄位類型
欄位text類型string
欄位segments[]類型object
欄位task_id類型string
欄位asset_url類型string
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。
回應server_error條件回傳的回應表示該作業或結果需要檢查下一步保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。

別名

模型別名

Ailoot qwen-audio-3.0-asr-flash, qwen-asr, qwen-asr-latest

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

qwen-audio-3.0-asr-flash, qwen-asr, qwen-asr-latest

", "method_identity": { "effective_request_model_id": "qwen-asr", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "qwen-asr", "route_label": "Core" }, "method_key": "Core|transcriptions|/v1/audio/transcriptions|qwen-asr", "ordinal": 1, "rawMethod": { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "回傳的回應表示該作業或結果需要檢查", "http_status": null, "recovery": "保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。", "type": "server_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.", "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": "保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。" }, "material_combinations": [ { "content_type": "multipart/form-data", "mode": "speech_to_text", "required": [ "actual audio file" ] } ], "media_library": { "asset": { "fields": [ { "description": null, "name": "asset_id", "type": "string" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "output_key", "type": "string" }, { "description": null, "name": "family", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "method", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "content_type", "type": "string" }, { "description": null, "name": "sha256", "type": "string" }, { "description": null, "name": "size_bytes", "type": "integer" }, { "description": null, "name": "content_url", "type": "string" } ], "http": "GET", "id_source": "actual returned asset_id", "path": "/v1/media/assets/{asset_id}" }, "content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "range_header_supported": true, "url_source": "Use exact returned signed content_url including its token; do not construct a token." }, "expired_link": { "code": "link_expired", "http_status": 404, "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate." }, "list": { "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.", "http": "GET", "output_fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "data", "type": "asset[]" }, { "description": null, "name": "next_cursor", "type": "string|null" } ], "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "family", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "cursor", "required": false, "type": "string" }, { "availability": "source_interface", "default": 20, "default_known": true, "enum": null, "enum_known": false, "maximum": 100, "minimum": 1, "name": "limit", "required": false, "type": "integer" } ], "path": "/v1/media/assets" }, "revoke": { "http": "DELETE", "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.", "path": "/v1/media/assets/{asset_id}", "pending_status": "revoking", "success_statuses": [ 202, 204 ] }, "task": { "http": "GET", "id_source": "actual returned task_id or media library record; operation_id is not task_id", "path": "/v1/media/tasks/{task_id}" } }, "operation_modes": [ "speech_to_text" ], "outputs": { "all_results": "請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。", "family": "transcription", "fields": [ { "description": null, "name": "text", "type": "string" }, { "description": null, "name": "segments[]", "type": "object" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "asset_url", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "qwen-asr" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "content_type": "multipart/form-data", "default": null, "default_known": false, "enum": null, "enum_known": false, "file_formats": [ "wav", "mp3", "m4a", "ogg", "webm", "flac" ], "maximum_bytes": 10485760, "maximum_seconds": 300, "name": "file", "required": true, "type": "file" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "material_types": [ "audio" ], "optional_controls": null, "required": null }, "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 for reconciliation without resubmission; no dedicated audio poll route." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "operation_modes": [ "audio_transcriptions" ], "output": { "family": [ "text" ], "format": null, "multioutputs": "retain every actual response output" } }, "ctx": null, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not f.is_file() or f.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose your actual MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n --form-string model=qwen-asr -F \"file=@$AILOOT_AUDIO_FILE\" \\\n -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Transcribe your actual recording", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_tool_calls": null, "out": null, "output": [ "text" ], "path": "/v1/audio/transcriptions", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.0021, "amount_unit": "usd_per_display_unit", "key": "audio_input_second", "label": "per minute of audio", "side": "in" } ] } ], "request_model_id": "qwen-asr", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "audio_input_second", "units": [ { "key": "audio_input_second", "label": "per minute of audio", "side": "in", "usd": 0.0021 } ] } }, { "html": "
Al

qwen-audio-3.0-asr-flash

Alibaba /qwen-asr-latest

入門

將音訊轉成易讀文字的語音辨識模型，會加入標點並將數字正規化。支援俄語及其他語言，也支援漢語方言。

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。

Qwen-Audio-3.0-ASR-Flash 用於將語音錄音轉成文字。Alibaba 著重多語言辨識及富有表現力的語音，包括詩歌節奏、文言文與文化敘事。輸入為音訊，結果為轉錄文字。

將語音寫成文字

模型會加入標點，並將口述數字、日期及金額轉成通用的書寫形式。適合語音訊息、訪談片段及教學語音，這些用途需要易讀文字，而不只是辨識出的詞語序列。

支援 30 種語言，包括俄語、英語、法語、德語、日語及阿拉伯語。另外涵蓋七大漢語方言系統，以及超過 20 種地區發音變體。此範圍用於辨識不同語言與口音的特徵。

針對專門術語，可提供任務背景及提示詞，協助引導人名與領域用語的辨識。此版本的時間戳記始終啟用，可將結果連結到錄音中的對應片段。短檔案的轉錄文字可一次完整回傳，也可隨處理進度逐步回傳。

素材與限制

錄音長度上限為五分鐘。每項任務使用一個檔案。支援 AAC、AMR、AVI、FLAC、FLV、M4A、MKV、MOV、MP3、MP4、MPEG、OGG、OPUS、WAV、WEBM、WMA 及 WMV；可使用任何取樣率。格式清單包含影片容器，是為了從其中的聲音部分擷取語音，不代表會對影格進行視覺分析。

Qwen-Audio-3.0-ASR-Flash 不支援依說話者區分內容或辨識情緒。主要結果是文字，以及辨識內容與錄音時間的對應關係。其他鄰近模型宣稱的較長錄音處理能力及其他音訊分析方式，不適用於此版本。

Ailoot 可用 · 輸入與方法

Ailoot · 語音轉文字 POST /v1/audio/transcriptions
輸入
audio
輸出
text
輸出格式
json
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
qwen-asr-latest
預設值—
欄位file類型file要求必填值與限制
位元組數上限: 10,485,760
檔案格式: wav, mp3, m4a, ogg, webm, flac
內容類型: multipart/form-data
時長上限（秒）: 300
預設值—
欄位response_format類型string要求選填值與限制
json
預設值—
輸入素材組合

speech_to_text · 必填： actual audio file

方法參數與生命週期
參數規格
參數material_types規格audio
參數required規格null
參數optional_controls規格null

生命週期： synchronous_result_then_owned_library

GET /v1/media/tasks/{task_id} · 實際回傳的 task_id 或媒體庫紀錄

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

GET /v1/media/assets

GET /v1/media/assets/{asset_id}

方法結構與 ID 均為精確值；供應商能力與准入狀態分開。

方案

Ailoot 方法費率

Ailoot 語音轉文字POST /v1/audio/transcriptions
輸入
US$0.0021 每分鐘音訊

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 · 語音轉文字

set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ["AILOOT_AUDIO_FILE"])\nif not f.is_file() or f.suffix.lower()!=".mp3":raise SystemExit("Choose your actual MP3 recording")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n  -H "Authorization: Bearer $AILOOT_API_KEY" \\\n  --form-string model=qwen-asr-latest -F "file=@$AILOOT_AUDIO_FILE" \\\n  -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path("result.json").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n

接收並儲存結果

Ailoot · 語音轉文字

json

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。

請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。

需要檢查原始回應時

保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。

回應欄位
欄位類型
欄位text類型string
欄位segments[]類型object
欄位task_id類型string
欄位asset_url類型string
欄位usage類型object
錯誤與後續步驟
回應條件下一步
回應400 · invalid_request_error條件必要欄位、素材表示方式或參數值無效下一步提出新的建立請求前，先修正指定欄位。
回應server_error條件回傳的回應表示該作業或結果需要檢查下一步保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。

別名

模型別名

Ailoot qwen-audio-3.0-asr-flash, qwen-asr, qwen-asr-latest

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

qwen-audio-3.0-asr-flash, qwen-asr, qwen-asr-latest

", "method_identity": { "effective_request_model_id": "qwen-asr-latest", "fmt": "transcriptions", "http": "POST", "path": "/v1/audio/transcriptions", "request_model_id": "qwen-asr-latest", "route_label": "Core" }, "method_key": "Core|transcriptions|/v1/audio/transcriptions|qwen-asr-latest", "ordinal": 2, "rawMethod": { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "回傳的回應表示該作業或結果需要檢查", "http_status": null, "recovery": "保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。", "type": "server_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.", "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": "保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。" }, "material_combinations": [ { "content_type": "multipart/form-data", "mode": "speech_to_text", "required": [ "actual audio file" ] } ], "media_library": { "asset": { "fields": [ { "description": null, "name": "asset_id", "type": "string" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "output_key", "type": "string" }, { "description": null, "name": "family", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "method", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "content_type", "type": "string" }, { "description": null, "name": "sha256", "type": "string" }, { "description": null, "name": "size_bytes", "type": "integer" }, { "description": null, "name": "content_url", "type": "string" } ], "http": "GET", "id_source": "actual returned asset_id", "path": "/v1/media/assets/{asset_id}" }, "content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "range_header_supported": true, "url_source": "Use exact returned signed content_url including its token; do not construct a token." }, "expired_link": { "code": "link_expired", "http_status": 404, "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate." }, "list": { "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.", "http": "GET", "output_fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "data", "type": "asset[]" }, { "description": null, "name": "next_cursor", "type": "string|null" } ], "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "family", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "cursor", "required": false, "type": "string" }, { "availability": "source_interface", "default": 20, "default_known": true, "enum": null, "enum_known": false, "maximum": 100, "minimum": 1, "name": "limit", "required": false, "type": "integer" } ], "path": "/v1/media/assets" }, "revoke": { "http": "DELETE", "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.", "path": "/v1/media/assets/{asset_id}", "pending_status": "revoking", "success_statuses": [ 202, 204 ] }, "task": { "http": "GET", "id_source": "actual returned task_id or media library record; operation_id is not task_id", "path": "/v1/media/tasks/{task_id}" } }, "operation_modes": [ "speech_to_text" ], "outputs": { "all_results": "請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。", "family": "transcription", "fields": [ { "description": null, "name": "text", "type": "string" }, { "description": null, "name": "segments[]", "type": "object" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "asset_url", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "qwen-asr-latest" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "content_type": "multipart/form-data", "default": null, "default_known": false, "enum": null, "enum_known": false, "file_formats": [ "wav", "mp3", "m4a", "ogg", "webm", "flac" ], "maximum_bytes": 10485760, "maximum_seconds": 300, "name": "file", "required": true, "type": "file" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "material_types": [ "audio" ], "optional_controls": null, "required": null }, "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 for reconciliation without resubmission; no dedicated audio poll route." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "operation_modes": [ "audio_transcriptions" ], "output": { "family": [ "text" ], "format": null, "multioutputs": "retain every actual response output" } }, "ctx": null, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not f.is_file() or f.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose your actual MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n --form-string model=qwen-asr-latest -F \"file=@$AILOOT_AUDIO_FILE\" \\\n -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Transcribe your actual recording", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_tool_calls": null, "out": null, "output": [ "text" ], "path": "/v1/audio/transcriptions", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.0021, "amount_unit": "usd_per_display_unit", "key": "audio_input_second", "label": "per minute of audio", "side": "in" } ] } ], "request_model_id": "qwen-asr-latest", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "audio_input_second", "units": [ { "key": "audio_input_second", "label": "per minute of audio", "side": "in", "usd": 0.0021 } ] } } ], "model_id": "qwen-audio-3.0-asr-flash", "nativeProvenance": { "input_facts_canonical_sha256": "df972e7211dc88278c079461d07341f6624a2aaf967c659e2b6eb041d0c5234e", "input_html_sha256": "ba80dde2506a5835238b8c7f37122a7676008c659f0688fe9faee4196ef4497a", "private_audit_sha256": "363dd1ccfa25aa0139bfb20701f4953ef86edd4d95566fdbb1ed1d7454caab75", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/zh-hant-tw/qwen-audio-3-0-asr-flash/", "description": "將音訊轉成易讀文字的語音辨識模型，會加入標點並將數字正規化。支援俄語及其他語言，也支援漢語方言。", "locale": "zh-hant-tw", "md_url": "https://ailoot.ai/models/zh-hant-tw/qwen-audio-3-0-asr-flash/index.md", "title": "qwen-audio-3.0-asr-flash — Ailoot", "url": "https://ailoot.ai/models/zh-hant-tw/qwen-audio-3-0-asr-flash/" }, "rawModel": { "about": "Qwen-Audio-3.0-ASR-Flash 用於將語音錄音轉成文字。Alibaba 著重多語言辨識及富有表現力的語音，包括詩歌節奏、文言文與文化敘事。輸入為音訊，結果為轉錄文字。\n\n### 將語音寫成文字\n\n模型會加入標點，並將口述數字、日期及金額轉成通用的書寫形式。適合語音訊息、訪談片段及教學語音，這些用途需要易讀文字，而不只是辨識出的詞語序列。\n\n支援 30 種語言，包括俄語、英語、法語、德語、日語及阿拉伯語。另外涵蓋七大漢語方言系統，以及超過 20 種地區發音變體。此範圍用於辨識不同語言與口音的特徵。\n\n針對專門術語，可提供任務背景及提示詞，協助引導人名與領域用語的辨識。此版本的時間戳記始終啟用，可將結果連結到錄音中的對應片段。短檔案的轉錄文字可一次完整回傳，也可隨處理進度逐步回傳。\n\n### 素材與限制\n\n錄音長度上限為五分鐘。每項任務使用一個檔案。支援 AAC、AMR、AVI、FLAC、FLV、M4A、MKV、MOV、MP3、MP4、MPEG、OGG、OPUS、WAV、WEBM、WMA 及 WMV；可使用任何取樣率。格式清單包含影片容器，是為了從其中的聲音部分擷取語音，不代表會對影格進行視覺分析。\n\nQwen-Audio-3.0-ASR-Flash 不支援依說話者區分內容或辨識情緒。主要結果是文字，以及辨識內容與錄音時間的對應關係。其他鄰近模型宣稱的較長錄音處理能力及其他音訊分析方式，不適用於此版本。", "alias_of": null, "aliases": [ "qwen-asr", "qwen-asr-latest" ], "author": "Alibaba", "ctx": null, "formats": [ "transcriptions" ], "id": "qwen-audio-3.0-asr-flash", "input": [ "audio" ], "kind": "transcription", "max_out": null, "methods": [ { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "回傳的回應表示該作業或結果需要檢查", "http_status": null, "recovery": "保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。", "type": "server_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.", "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": "保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。" }, "material_combinations": [ { "content_type": "multipart/form-data", "mode": "speech_to_text", "required": [ "actual audio file" ] } ], "media_library": { "asset": { "fields": [ { "description": null, "name": "asset_id", "type": "string" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "output_key", "type": "string" }, { "description": null, "name": "family", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "method", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "content_type", "type": "string" }, { "description": null, "name": "sha256", "type": "string" }, { "description": null, "name": "size_bytes", "type": "integer" }, { "description": null, "name": "content_url", "type": "string" } ], "http": "GET", "id_source": "actual returned asset_id", "path": "/v1/media/assets/{asset_id}" }, "content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "range_header_supported": true, "url_source": "Use exact returned signed content_url including its token; do not construct a token." }, "expired_link": { "code": "link_expired", "http_status": 404, "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate." }, "list": { "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.", "http": "GET", "output_fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "data", "type": "asset[]" }, { "description": null, "name": "next_cursor", "type": "string|null" } ], "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "family", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "cursor", "required": false, "type": "string" }, { "availability": "source_interface", "default": 20, "default_known": true, "enum": null, "enum_known": false, "maximum": 100, "minimum": 1, "name": "limit", "required": false, "type": "integer" } ], "path": "/v1/media/assets" }, "revoke": { "http": "DELETE", "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.", "path": "/v1/media/assets/{asset_id}", "pending_status": "revoking", "success_statuses": [ 202, 204 ] }, "task": { "http": "GET", "id_source": "actual returned task_id or media library record; operation_id is not task_id", "path": "/v1/media/tasks/{task_id}" } }, "operation_modes": [ "speech_to_text" ], "outputs": { "all_results": "請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。", "family": "transcription", "fields": [ { "description": null, "name": "text", "type": "string" }, { "description": null, "name": "segments[]", "type": "object" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "asset_url", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "qwen-audio-3.0-asr-flash" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "content_type": "multipart/form-data", "default": null, "default_known": false, "enum": null, "enum_known": false, "file_formats": [ "wav", "mp3", "m4a", "ogg", "webm", "flac" ], "maximum_bytes": 10485760, "maximum_seconds": 300, "name": "file", "required": true, "type": "file" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "material_types": [ "audio" ], "optional_controls": null, "required": null }, "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 for reconciliation without resubmission; no dedicated audio poll route." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "operation_modes": [ "audio_transcriptions" ], "output": { "family": [ "text" ], "format": null, "multioutputs": "retain every actual response output" } }, "ctx": null, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not f.is_file() or f.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose your actual MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n --form-string model=qwen-audio-3.0-asr-flash -F \"file=@$AILOOT_AUDIO_FILE\" \\\n -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Transcribe your actual recording", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_tool_calls": null, "out": null, "output": [ "text" ], "path": "/v1/audio/transcriptions", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.0021, "amount_unit": "usd_per_display_unit", "key": "audio_input_second", "label": "per minute of audio", "side": "in" } ] } ], "request_model_id": "qwen-audio-3.0-asr-flash", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "audio_input_second", "units": [ { "key": "audio_input_second", "label": "per minute of audio", "side": "in", "usd": 0.0021 } ] }, { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "回傳的回應表示該作業或結果需要檢查", "http_status": null, "recovery": "保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。", "type": "server_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.", "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": "保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。" }, "material_combinations": [ { "content_type": "multipart/form-data", "mode": "speech_to_text", "required": [ "actual audio file" ] } ], "media_library": { "asset": { "fields": [ { "description": null, "name": "asset_id", "type": "string" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "output_key", "type": "string" }, { "description": null, "name": "family", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "method", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "content_type", "type": "string" }, { "description": null, "name": "sha256", "type": "string" }, { "description": null, "name": "size_bytes", "type": "integer" }, { "description": null, "name": "content_url", "type": "string" } ], "http": "GET", "id_source": "actual returned asset_id", "path": "/v1/media/assets/{asset_id}" }, "content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "range_header_supported": true, "url_source": "Use exact returned signed content_url including its token; do not construct a token." }, "expired_link": { "code": "link_expired", "http_status": 404, "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate." }, "list": { "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.", "http": "GET", "output_fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "data", "type": "asset[]" }, { "description": null, "name": "next_cursor", "type": "string|null" } ], "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "family", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "cursor", "required": false, "type": "string" }, { "availability": "source_interface", "default": 20, "default_known": true, "enum": null, "enum_known": false, "maximum": 100, "minimum": 1, "name": "limit", "required": false, "type": "integer" } ], "path": "/v1/media/assets" }, "revoke": { "http": "DELETE", "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.", "path": "/v1/media/assets/{asset_id}", "pending_status": "revoking", "success_statuses": [ 202, 204 ] }, "task": { "http": "GET", "id_source": "actual returned task_id or media library record; operation_id is not task_id", "path": "/v1/media/tasks/{task_id}" } }, "operation_modes": [ "speech_to_text" ], "outputs": { "all_results": "請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。", "family": "transcription", "fields": [ { "description": null, "name": "text", "type": "string" }, { "description": null, "name": "segments[]", "type": "object" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "asset_url", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "qwen-asr" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "content_type": "multipart/form-data", "default": null, "default_known": false, "enum": null, "enum_known": false, "file_formats": [ "wav", "mp3", "m4a", "ogg", "webm", "flac" ], "maximum_bytes": 10485760, "maximum_seconds": 300, "name": "file", "required": true, "type": "file" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "material_types": [ "audio" ], "optional_controls": null, "required": null }, "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 for reconciliation without resubmission; no dedicated audio poll route." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "operation_modes": [ "audio_transcriptions" ], "output": { "family": [ "text" ], "format": null, "multioutputs": "retain every actual response output" } }, "ctx": null, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not f.is_file() or f.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose your actual MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n --form-string model=qwen-asr -F \"file=@$AILOOT_AUDIO_FILE\" \\\n -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Transcribe your actual recording", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_tool_calls": null, "out": null, "output": [ "text" ], "path": "/v1/audio/transcriptions", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.0021, "amount_unit": "usd_per_display_unit", "key": "audio_input_second", "label": "per minute of audio", "side": "in" } ] } ], "request_model_id": "qwen-asr", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "audio_input_second", "units": [ { "key": "audio_input_second", "label": "per minute of audio", "side": "in", "usd": 0.0021 } ] }, { "cache_read": null, "cache_write": null, "cache_write_1h": null, "cache_write_5m": null, "conditional_meter": null, "contract": { "data": { "all_results": "Retain complete JSON, not only text; preserve every available segment/speaker/timestamp and actual task/asset identity.", "errors": [ { "code": null, "condition": "必要欄位、素材表示方式或參數值無效", "http_status": 400, "recovery": "提出新的建立請求前，先修正指定欄位。", "type": "invalid_request_error" }, { "code": null, "condition": "回傳的回應表示該作業或結果需要檢查", "http_status": null, "recovery": "保留原始回傳的作業／任務 ID、請求標頭與回應；繼續以支援的方式讀取該原始作業。請勿重新提交建立請求。", "type": "server_error" } ], "hints": [], "ignored_fields": [], "lifecycle": { "all_results": "Follow everyactualreturnedoutputandownedasset; no result is discardedbecauseindex0orcontent_urlalreadyexists.", "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": "保留原始 operation_id/X-Client-Request-ID 以供核對，請勿重新提交；沒有專用的音訊輪詢路由。" }, "material_combinations": [ { "content_type": "multipart/form-data", "mode": "speech_to_text", "required": [ "actual audio file" ] } ], "media_library": { "asset": { "fields": [ { "description": null, "name": "asset_id", "type": "string" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "output_key", "type": "string" }, { "description": null, "name": "family", "type": "string" }, { "description": null, "name": "model", "type": "string" }, { "description": null, "name": "method", "type": "string" }, { "description": null, "name": "status", "type": "string" }, { "description": null, "name": "content_type", "type": "string" }, { "description": null, "name": "sha256", "type": "string" }, { "description": null, "name": "size_bytes", "type": "integer" }, { "description": null, "name": "content_url", "type": "string" } ], "http": "GET", "id_source": "actual returned asset_id", "path": "/v1/media/assets/{asset_id}" }, "content": { "http": "GET", "path": "/v1/media/assets/{asset_id}/content", "range_header_supported": true, "url_source": "Use exact returned signed content_url including its token; do not construct a token." }, "expired_link": { "code": "link_expired", "http_status": 404, "recovery": "Read the asset again to obtain its refreshed signed content_url, then fetch that URL. Do not regenerate." }, "list": { "all_pages": "Follow every returned next_cursor, then select records by their actual task_id/output_key.", "http": "GET", "output_fields": [ { "description": null, "name": "object", "type": "string" }, { "description": null, "name": "data", "type": "asset[]" }, { "description": null, "name": "next_cursor", "type": "string|null" } ], "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "family", "required": false, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "cursor", "required": false, "type": "string" }, { "availability": "source_interface", "default": 20, "default_known": true, "enum": null, "enum_known": false, "maximum": 100, "minimum": 1, "name": "limit", "required": false, "type": "integer" } ], "path": "/v1/media/assets" }, "revoke": { "http": "DELETE", "meaning": "Revokes/deletes the existing owned file; this is not generation cancellation.", "path": "/v1/media/assets/{asset_id}", "pending_status": "revoking", "success_statuses": [ 202, 204 ] }, "task": { "http": "GET", "id_source": "actual returned task_id or media library record; operation_id is not task_id", "path": "/v1/media/tasks/{task_id}" } }, "operation_modes": [ "speech_to_text" ], "outputs": { "all_results": "請保留完整 JSON，而非僅保留文字；所有可用的片段／說話者／時間戳記與實際工作／資產身分均須保留。", "family": "transcription", "fields": [ { "description": null, "name": "text", "type": "string" }, { "description": null, "name": "segments[]", "type": "object" }, { "description": null, "name": "task_id", "type": "string" }, { "description": null, "name": "asset_url", "type": "string" }, { "description": null, "name": "usage", "type": "object" } ], "format": "json" }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "qwen-asr-latest" ], "enum_known": true, "name": "model", "required": true, "type": "string" }, { "availability": "source_interface", "content_type": "multipart/form-data", "default": null, "default_known": false, "enum": null, "enum_known": false, "file_formats": [ "wav", "mp3", "m4a", "ogg", "webm", "flac" ], "maximum_bytes": 10485760, "maximum_seconds": 300, "name": "file", "required": true, "type": "file" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "json" ], "enum_known": true, "name": "response_format", "required": false, "type": "string" } ], "profile_binding": "Exact existing Ailoot model and method; interface constraints below do not assert provider qualification.", "unsupported": [] }, "hints": [ "方法結構與 ID 均為精確值；供應商能力與准入狀態分開。" ], "input": { "material_types": [ "audio" ], "optional_controls": null, "required": null }, "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 for reconciliation without resubmission; no dedicated audio poll route." }, "method": { "http": "POST", "path": "/v1/audio/transcriptions" }, "operation_modes": [ "audio_transcriptions" ], "output": { "family": [ "text" ], "format": null, "multioutputs": "retain every actual response output" } }, "ctx": null, "examples": [ { "code": "set -eu\n: \"${AILOOT_API_KEY:?Set your Ailoot API key}\"\n: \"${AILOOT_AUDIO_FILE:?Set your actual MP3 recording}\"\nexport AILOOT_AUDIO_FILE\npython3 - <<'PY_REQUEST'\nimport os\nfrom pathlib import Path\nf=Path(os.environ[\"AILOOT_AUDIO_FILE\"])\nif not f.is_file() or f.suffix.lower()!=\".mp3\":raise SystemExit(\"Choose your actual MP3 recording\")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/audio/transcriptions \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" \\\n --form-string model=qwen-asr-latest -F \"file=@$AILOOT_AUDIO_FILE\" \\\n -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nprint(json.dumps(json.loads(Path(\"result.json\").read_text()),ensure_ascii=False,indent=2))\nPY_RESULT\n", "label": "Transcribe your actual recording", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "transcriptions", "http": "POST", "img_in": null, "img_out": null, "in": null, "input": [ "audio" ], "label": "語音轉文字", "max_out": null, "max_tool_calls": null, "out": null, "output": [ "text" ], "path": "/v1/audio/transcriptions", "pricing_profiles": [ { "dimensions": {}, "label": "Core", "units": [ { "amount": 0.0021, "amount_unit": "usd_per_display_unit", "key": "audio_input_second", "label": "per minute of audio", "side": "in" } ] } ], "request_model_id": "qwen-asr-latest", "route_label": "Core", "status_reads": [], "tiers": [], "tool_prices": null, "unit": "audio_input_second", "units": [ { "key": "audio_input_second", "label": "per minute of audio", "side": "in", "usd": 0.0021 } ] } ], "model_aliases": [ { "canonical_model_id": "qwen-audio-3.0-asr-flash", "request_model_id": "qwen-audio-3.0-asr-flash", "route_label": "Core" }, { "canonical_model_id": "qwen-audio-3.0-asr-flash", "request_model_id": "qwen-asr", "route_label": "Core" }, { "canonical_model_id": "qwen-audio-3.0-asr-flash", "request_model_id": "qwen-asr-latest", "route_label": "Core" } ], "name": "qwen-audio-3.0-asr-flash", "price": { "in": 0.0021, "in_label": "per minute of audio", "out": null, "out_label": null, "sort_in": null, "sort_out": null, "varies": false }, "short": "將音訊轉成易讀文字的語音辨識模型，會加入標點並將數字正規化。支援俄語及其他語言，也支援漢語方言。" }, "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 }, { "contract_json_pointer": "/methods/1/rawMethod/contract", "html_json_pointer": "/methods/1/html", "method_ordinal": 1 }, { "contract_json_pointer": "/methods/2/rawMethod/contract", "html_json_pointer": "/methods/2/html", "method_ordinal": 2 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod", "/methods/1/rawMethod", "/methods/2/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "將音訊轉成易讀文字的語音辨識模型，會加入標點並將數字正規化。支援俄語及其他語言，也支援漢語方言。", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "e57e6c3cbb391613d6c5c199f0d9e34beb4ac5df1cbf3ff4e404575012ac7256", "renderer_sha256": "13a3fc1b22d07359278e2249d630bfc9bb9e6416c71ba53def933fb5a903660b" }, "sourceRevision": "c862b794b94cd89e667ffb8ae983c18ffedea308fc79457afa4fcb4cf2bcc063" }