Sociaro

groq/whisper-large-v3-turbo

OpenAI's Whisper large-v3-turbo speech-to-text, run on Groq: the fastest Whisper variant, tuned for speed with high accuracy, in 99+ languages.

Takes flac, mp3, m4a, mpeg, mpga, ogg, wav or webm.

Sluggroq/whisper-large-v3-turbo
Kindtranscription
Vendorgroq
EndpointPOST /v1/audio/transcriptions

Charged per job from what the generator reports it rendered — your Logs show the exact figure for each one; see balance and billing.

Calling it

curl https://api.sociaro.com/v1/audio/transcriptions \
  -H "Authorization: Bearer $SOCIARO_API_KEY" \
  -F model=groq/whisper-large-v3-turbo \
  -F file=@./recording.mp3

Parameters

FieldTypeRequiredDefaultValuesWhat it does
fileaudio file (multipart)yes—flac · mp3 · m4a · mpeg · mpga · ogg · wav · webmThe recording to transcribe, sent as a multipart form field.
languagestringnodetectedan ISO-639-1 code, e.g. en, de, ruThe spoken language. Naming it improves accuracy and speed; leave it out to let the model detect it.
promptstringno—textContext or spelling to steer the transcript, such as names and terms, in the audio's language.
response_formatstringnojsonjson · verbose_json · text`verbose_json` adds segments with timestamps.
temperaturenumberno00 – 1Higher is more varied; 0 is the most deterministic.