POST
/
audio
/
transcriptions
Transcribe Audio
curl --request POST \
  --url https://{controlPlaneURL}/api/llm/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form 'file=<any>' \
  --form 'model=<string>' \
  --form chunking_strategy=auto \
  --form 'include=<string>' \
  --form 'language=<string>' \
  --form 'prompt=<string>' \
  --form 'response_format=<string>' \
  --form temperature=123 \
  --form timestamp_granularities=word
{
  "text": "<string>"
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Headers

x-tfy-metadata
string

Optional metadata for the request

Body

multipart/form-data

Audio file to transcribe and transcription options

model
string
required

Identifier of the model to be used for generation.

file
any

Audio file to transcribe: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.

chunking_strategy

Controls audio chunking. "auto" uses VAD to select boundaries.

Available options:
auto
include
string[]

Additional info to include (e.g. logprobs for model confidence).

language
string

Input audio language in ISO-639-1 format (e.g. en).

prompt
string

Text to guide model style or continue a previous segment.

response_format
string

Output format: json, text, srt, verbose_json, or vtt. Default: json.

temperature
number

Sampling temperature (0-1). Higher values increase randomness. Default: 0.

timestamp_granularities
enum<string>[]

Timestamp detail level: word or segment. Default: ["segment"].

Response

Audio transcribed successfully

text
string
required

The transcribed text.