OpenAI
Whisper large v3 Turbo speech to text
Whisper large v3 Turbo runs on Groq and prioritizes transcription speed. It turns multilingual recordings into text in the original language.
Model interface
API model ID
groq/whisper-large-v3-turbo- Input
- Audio file
- Output
- Transcript
- Endpoint
POST /v1/audio/transcriptions
Best for
- Produce first-pass transcripts for a podcast backlog
- Turn a newly uploaded voice note into searchable text
Technical details
Read the model documentation- API model ID
groq/whisper-large-v3-turbo- Provider
- OpenAI
- Modality
- Audio
- Input
- Audio file
- Output
- Transcript
- Endpoint
POST /v1/audio/transcriptions- Response formats
- json · verbose_json · text
Request parameters
fileaudio file (multipart) · RequiredThe recording to transcribe, sent as a multipart form field.
- flac
- mp3
- m4a
- mpeg
- mpga
- ogg
- wav
- webm
promptstring · OptionalContext or spelling to steer the transcript, such as names and terms, in the audio's language.
text
languagestring · Optional · Default: detectedThe spoken language. Naming it improves accuracy and speed; leave it out to let the model detect it.
an ISO-639-1 code, e.g. en, de, ru
response_formatstring · Optional · Default: jsonverbose_json adds segments with timestamps.
- json
- verbose_json
- text
temperaturenumber · Optional · Default: 0Higher is more varied; 0 is the most deterministic.
0 – 1
Pricing
| Billable unit and options | Rate (USD) |
|---|---|
| Per hour of input audiobilled at $0.000013333333 a second | $0.048 |
Billing notes
- Runs on Groq.
Catalogue rates on 21 Nov 2026. Prices exclude VAT.
View in pricing catalogue