Audio transcription create (deprecated)

post deprecated

https://api.macpaw.com/v1/audio/transcriptions

Deprecated. Use POST /v2/audio/transcriptions instead.

Transcribes audio with an OpenAI or ElevenLabs model. Fields marked with a provider apply only to that provider's models.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Body Params

file

required

Audio or video file to transcribe.

model

string

required

Model id in provider/model format.

language

string

OpenAI only — ISO-639-1 language of the audio. ElevenLabs models use language_code.

language_code

string

ElevenLabs only — ISO-639-1 or ISO-639-3 language code; omit to auto-detect.

prompt

string

OpenAI only — text that guides the style or continues a previous segment.

response_format

string

OpenAI only — json, text, srt, verbose_json, vtt or diarized_json.

stream

boolean

OpenAI only — return text/event-stream. Not supported by whisper-1.

temperature

number

Sampling temperature. ElevenLabs accepts 0 to 2.

num_speakers

integer

ElevenLabs only — maximum number of speakers, up to 32.

keyterms

array of strings

ElevenLabs only — terms to bias recognition toward, up to 1000.

keyterms

use_multi_channel

boolean

ElevenLabs only — transcribe each channel separately (up to 5); the response has transcripts[].

Headers

string

enum

Defaults to application/json

Generated from available response content types

Allowed:

Responses

200The provider's transcription. The shape depends on the provider, the model and response_format.

400Bad request — invalid file or parameters

401Invalid token

402Insufficient credits

403Forbidden — authenticated but not allowed to access the requested model