supermarket

Transcribe audio

Groq speech to text

Hosted Whisper speech-to-text API that transcribes audio files, or translates them to English, with OpenAI-compatible endpoints.

Rate limits

Base Developer plan limits for both Whisper models. ASH is audio seconds per hour, ASD per day.

ModelRPMRPDASHASD
whisper-large-v3202K7.2K28.8K
whisper-large-v3-turbo202K7.2K28.8K

Source4Rate limits

Other limits

Over the limit
HTTP 429 with a retry-after header4
Prompt length
224 tokens1
Minimum file length
0.01 seconds1
Scope of limits
Per organization4

Read from Groq’s own pages on 2026-11-04. Every number links to the page a value came from. For agents, the same facts as markdown: /tools/transcribe-audio/groq-speech-to-text.md