Перейти к содержимому

Transcribe audio

POST
/audio/transcriptions
curl --request POST \
--url https://example.com/audio/transcriptions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: multipart/form-data' \
--form file=example \
--form model=whisper-1 \
--form language=example \
--form response_format=json

OpenAI-compatible STT (multipart: file + model). Served by whisper-large-v3-turbo. Returns {"text": ...} (or plain text if response_format=text). Charged per minute of audio. Max file size 25 MB.

Media typemultipart/form-data
Body_create_transcription
object
file
required
File
string
model
Model
string
default: whisper-1
language
Any of:
string
response_format
Response Format
string
default: json

Successful Response

Media typeapplication/json
Examplegenerated
example

Validation Error

Media typeapplication/json
HTTPValidationError
object
detail
Detail
Array<object>
ValidationError
object
loc
required
Location
Array
msg
required
Message
string
type
required
Error Type
string
input
Input
ctx
Context
object
Examplegenerated
{
"detail": [
{
"loc": [
"example"
],
"msg": "example",
"type": "example",
"input": "example",
"ctx": {}
}
]
}