Skip to content
LinkInfra
Console
HomeModels
DocsAudio & speech

Audio transcriptions

Upload an audio file and transcribe it into text using multipart/form-data.

OpenAI compatible
POST/v1/audio/transcriptions
Base URLhttps://api.linkinfra.ai
AuthorizationBodyResponse

Authorization

Bearer Token
AuthorizationBearer <token>

Authenticate requests with your API key in the request header:

Authorization: Bearer sk-your-api-key

Need a key? Create one in the console

Let the HTTP client generate the multipart boundary. Do not manually set Content-Type for file uploads.

Request body

multipart/form-data
modelstringrequired

Model ID from the model catalog. Availability depends on your account group and configured channels.

filefilerequired

An audio file, such as mp3, wav, or m4a. File size and format limits depend on the upstream.

languagestring

ISO-639-1 language code, such as zh or en.

promptstring

Optional context to guide transcription style and proper nouns.

response_formatstring

Response format, such as json or text, subject to model support.

Response

application/json
200Successful response
textstring

Transcribed text. The example uses the default JSON response format.

Request failed? Read the error handling guide