SPEECH TO TEXT API
Transcribe audio with a single API call.
Send an audio file, get a transcript back. Whisper Large v3, Whisper Large v3 Turbo and Voxtral Small behind one OpenAI-compatible endpoint, billed per minute of audio.
Hand this to your agent
Add a Runcrate model to this project: run curl -fsSL"https://runcrate.ai/agents.md?intent=build"and follow it.
Your agent asks for an API key. Create a key
Quick start
Hand it to your agent. Or read the request it sends.
Your agent writes and runs it. The same key works for every model and every GPU.
Available models
Models you can call today. Billed prices, as charged.
| Model | Maker | Price | Detail |
|---|---|---|---|
| openai/whisper-large-v3 | OpenAI | $0.000473 per minute | Full model, 100+ languages |
| openai/whisper-large-v3-turbo | OpenAI | $0.00021 per minute | 8x faster, near-identical accuracy |
| mistralai/Voxtral-Small-24B-2507 | Mistral | $0.00315 per minute | Strong multilingual, long-form audio |
Why Runcrate
Built for production. One key, one balance.
100+ languages
Whisper Large v3 supports over 100 languages and dialects out of the box, with automatic language detection.
OpenAI-compatible
Drop-in replacement for the OpenAI Whisper API. Point the OpenAI client at Runcrate's base URL and existing transcription calls keep working.
Per-minute billing
Pay only for audio processed, per minute at each model's listed price. No subscriptions, no seat licenses, no minimum spend.
Long-form audio
Upload files up to 25MB. Podcast episodes, meeting recordings, lecture captures, and call-center logs transcribed end to end.
Comparison
Runcrate and OpenAI, side by side.
| Feature | Runcrate | OpenAI |
|---|---|---|
| Whisper Large v3 price | $0.000473 per minute | $0.006/min |
| Turbo model price | $0.00021 per minute | Not offered |
| OpenAI-compatible | Yes | Native |
| Alternative models | Voxtral Small + more | OpenAI models only |
FAQ
Common questions.
Related