> For the complete documentation index, see [llms.txt](https://guides.ia.numerique.gouv.fr/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guides.ia.numerique.gouv.fr/albert-api/api-reference/liste-des-endpoint/audio.md).
# Audio
## POST /v1/audio/transcriptions
> Create Audio Transcription
```json
{"openapi":"3.1.0","info":{"title":"Albert API","version":"0.8.0"},"tags":[{"name":"Audio"}],"servers":[{"url":"https://albert.api.etalab.gouv.fr"}],"security":[{"HTTPBearer":[]}],"components":{"securitySchemes":{"HTTPBearer":{"type":"http","scheme":"bearer"}},"schemas":{"Body_create_audio_transcription_v1_audio_transcriptions_post":{"properties":{"file":{"type":"string","contentMediaType":"application/octet-stream","title":"File","description":"The audio file object (not file name) to transcribe, in one of these formats: mp3 or wav."},"model":{"type":"string","title":"Model","description":"ID of the model to use. Call `/v1/models` endpoint to get the list of available models, only `automatic-speech-recognition` model type is supported."},"language":{"anyOf":[{"$ref":"#/components/schemas/AudioTranscriptionLanguage"},{"type":"null"}],"description":"The language of the output audio. If the output language is different than the audio language, the audio language will be translated into the output language. Output language must be supplied in ISO-639-1 format (e.g. en, fr) format."},"prompt":{"type":"string","title":"Prompt","description":"An optional text to tell the model what to do with the input audio.","default":""},"response_format":{"$ref":"#/components/schemas/AudioTranscriptionsResponseFormat","description":"The format of the transcript output: `json` (default), `text`, `diarized_json` to return per-segment speaker labels, `srt` or `vtt` for subtitle formats.","default":"json"},"temperature":{"type":"number","maximum":1,"minimum":0,"title":"Temperature","description":"The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use log probability to automatically increase the temperature until certain thresholds are hit.","default":0}},"type":"object","required":["file","model"],"title":"Body_create_audio_transcription_v1_audio_transcriptions_post"},"AudioTranscriptionLanguage":{"type":"string","enum":["af","afrikaans","albanian","am","amharic","ar","arabic","armenian","as","assamese","az","azerbaijani","ba","bashkir","basque","be","belarusian","bengali","bg","bn","bo","bosnian","br","breton","bs","bulgarian","burmese","ca","cantonese","castilian","catalan","chinese","croatian","cs","cy","czech","da","danish","de","dutch","el","en","english","es","estonian","et","eu","fa","faroese","fi","finnish","flemish","fo","fr","french","galician","georgian","german","gl","greek","gu","gujarati","ha","haitian","haitian creole","hausa","haw","hawaiian","he","hebrew","hi","hindi","hr","ht","hu","hungarian","hy","icelandic","id","indonesian","is","it","italian","ja","japanese","javanese","jw","ka","kannada","kazakh","khmer","kk","km","kn","ko","korean","la","lao","latin","latvian","lb","letzeburgesch","lingala","lithuanian","ln","lo","lt","luxembourgish","lv","macedonian","malagasy","malay","malayalam","maltese","mandarin","maori","marathi","mg","mi","mk","ml","mn","moldavian","moldovan","mongolian","mr","ms","mt","my","myanmar","ne","nepali","nl","nn","no","norwegian","nynorsk","oc","occitan","pa","panjabi","pashto","persian","pl","polish","portuguese","ps","pt","punjabi","pushto","ro","romanian","ru","russian","sa","sanskrit","sd","serbian","shona","si","sindhi","sinhala","sinhalese","sk","sl","slovak","slovenian","sn","so","somali","spanish","sq","sr","su","sundanese","sv","sw","swahili","swedish","ta","tagalog","tajik","tamil","tatar","te","telugu","tg","th","thai","tibetan","tk","tl","tr","tt","turkish","turkmen","uk","ukrainian","ur","urdu","uz","uzbek","valencian","vi","vietnamese","welsh","yi","yiddish","yo","yoruba","yue","zh"],"title":"AudioTranscriptionLanguage"},"AudioTranscriptionsResponseFormat":{"type":"string","enum":["json","text","verbose_json","diarized_json","srt","vtt"],"title":"AudioTranscriptionsResponseFormat"},"AudioTranscriptionsResponse":{"properties":{"id":{"type":"string","title":"Id","description":"A unique identifier for the audio transcription."},"text":{"type":"string","title":"Text","description":"The transcription text."},"model":{"type":"string","title":"Model","description":"The model used to generate the transcription."},"segments":{"anyOf":[{"items":{"$ref":"#/components/schemas/Segment"},"type":"array"},{"type":"null"}],"title":"Segments","description":"Diarized segments, only set when `response_format=diarized_json`."},"usage":{"$ref":"#/components/schemas/api__domain__usage__entities__Usage","description":"Usage information for the request."}},"additionalProperties":true,"type":"object","required":["id","text","model"],"title":"AudioTranscriptionsResponse"},"Segment":{"properties":{"id":{"type":"integer","title":"Id","description":"A unique identifier for the segment."},"type":{"type":"string","title":"Type","description":"The type of the segment.","default":"transcript.text.segment"},"text":{"type":"string","title":"Text","description":"The segment text."},"start":{"type":"number","title":"Start","description":"Start time of the segment in seconds."},"end":{"type":"number","title":"End","description":"End time of the segment in seconds."},"speaker":{"anyOf":[{"type":"string"},{"type":"null"}],"title":"Speaker","description":"Speaker label assigned by diarization, if available."}},"additionalProperties":true,"type":"object","required":["id","text","start","end"],"title":"Segment"},"api__domain__usage__entities__Usage":{"properties":{"prompt_tokens":{"type":"integer","title":"Prompt Tokens","default":0},"completion_tokens":{"type":"integer","title":"Completion Tokens","default":0},"total_tokens":{"type":"integer","title":"Total Tokens","default":0},"cost":{"type":"number","title":"Cost","default":0},"impacts":{"$ref":"#/components/schemas/api__domain__usage__entities__EnvironmentalImpacts","default":{"kWh":0,"kgCO2eq":0}}},"additionalProperties":true,"type":"object","title":"Usage"},"api__domain__usage__entities__EnvironmentalImpacts":{"properties":{"kWh":{"type":"number","title":"Kwh","default":0},"kgCO2eq":{"type":"number","title":"Kgco2Eq","default":0}},"additionalProperties":true,"type":"object","title":"EnvironmentalImpacts"},"api__infrastructure__fastapi__documentation__HTTPExceptionModel":{"properties":{"status_code":{"type":"integer","title":"Status Code"},"detail":{"type":"string","title":"Detail"},"headers":{"anyOf":[{"additionalProperties":{"type":"string"},"type":"object"},{"type":"null"}],"title":"Headers"}},"type":"object","required":["status_code","detail"],"title":"HTTPExceptionModel"}}},"paths":{"/v1/audio/transcriptions":{"post":{"tags":["Audio"],"summary":"Create Audio Transcription","operationId":"create_audio_transcription_v1_audio_transcriptions_post","requestBody":{"content":{"multipart/form-data":{"schema":{"$ref":"#/components/schemas/Body_create_audio_transcription_v1_audio_transcriptions_post"}}},"required":true},"responses":{"200":{"description":"Successful Response","content":{"application/json":{"schema":{"$ref":"#/components/schemas/AudioTranscriptionsResponse"}}}},"400":{"description":"Insufficient budget.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"401":{"description":"Invalid authentication scheme.
Invalid API key.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"403":{"description":"Your account has expired. Please contact support to renew your account.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"404":{"description":"Model {name} not found.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"413":{"description":"File size limit exceeded. Expected: {expected_size}. Actual: {size}.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"422":{"description":"Model has wrong type. Expected: {expected_type}. Actual: {actual_type}.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"429":{"description":"Token/request limit per minute/day exceeded.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}},"503":{"description":"Model is too busy, please try again later.","content":{"application/json":{"schema":{"$ref":"#/components/schemas/api__infrastructure__fastapi__documentation__HTTPExceptionModel"}}}}}}}}}
```
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://guides.ia.numerique.gouv.fr/albert-api/api-reference/liste-des-endpoint/audio.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.