Skip to main content
POST
/
v1
/
audio
/
transcriptions
Transcribe audio
curl --request POST \
  --url https://api.pyai.com/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form model=pyai-hear \
  --form response_format=json \
  --form 'language=<string>' \
  --form seed=123 \
  --form temperature=123
{
  "text": "<string>",
  "model": "<string>"
}

Authorizations

​
Authorization
string
header
required

Use Authorization: Bearer pyai_live_... (or pyai_test_...).

Body

multipart/form-data
​
file
file
required

Audio file (wav, mp3, m4a, flac, ogg).

​
model
string
default:pyai-hear
​
response_format
enum<string>
default:json
Available options:
json,
text,
verbose_json
​
language
string

ISO-639-1 hint, e.g. 'en'.

​
seed
integer

Optional determinism seed for reproducible eval runs. Forwarded to the engine and honored once the engine supports it (PLATFORM_ASK_EVALS_ENGINE); no effect when omitted.

​
temperature
number

Optional sampling temperature for reproducible eval runs. Forwarded to the engine and honored once the engine supports it (PLATFORM_ASK_EVALS_ENGINE); no effect when omitted.

Response

Transcription result

​
text
string
​
model
string