SPEECH TO TEXT API
Transcribe audio with a single API call.
Production-grade speech-to-text powered by Whisper Large V3, Whisper V3 Turbo, and Voxtral Small. OpenAI-compatible endpoint, per-minute billing, and no minimum commitments. Upload an audio file, get a transcript back in seconds.
QUICK START
Integrate in minutes.
from openai import OpenAI
client = OpenAI(
base_url="https://api.runcrate.ai/v1",
api_key="rc_live_YOUR_API_KEY",
)
transcript = client.audio.transcriptions.create(
model="openai/whisper-large-v3",
file=open("meeting.mp3", "rb"),
)
print(transcript.text)AVAILABLE MODELS
Models you can use today.
| Model | Provider | Price | Detail |
|---|---|---|---|
| openai/whisper-large-v3 | OpenAI | $0.045/min | Highest accuracy, 100+ languages |
| openai/whisper-large-v3-turbo | OpenAI | $0.02/min | 8x faster, near-identical accuracy |
| mistralai/Voxtral-Small | Mistral | $0.03/min | Strong multilingual, long-form audio |
WHY RUNCRATE
Built for production.
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. Change one line of code and your existing integration works immediately.
Per-Minute Billing
Pay only for audio processed. No subscriptions, no seat licenses, no minimum spend. Credits never expire.
Long-Form Audio
Upload files up to 25MB. Podcast episodes, meeting recordings, lecture captures, and call-center logs transcribed end to end.
COMPARISON
Runcrate vs OpenAI.
| Feature | Runcrate | OpenAI |
|---|---|---|
| Whisper Large V3 price | $0.045/min | $0.006/min |
| Turbo model price | $0.02/min | N/A |
| OpenAI-compatible | Yes | Native |
| Alternative models | Voxtral Small + more | Whisper only |
| Rate limits | Generous | Strict tiers |
FAQ