Speech-to-Text API
Transcribe audio through one API — upload a file, pass the URL, and get text back with the same auth and request lifecycle as every other model on the platform.
2 speech-to-text models available right now — every one runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant via MCP.
Speech-to-Text models & pricing
| Model | Endpoint | Price |
|---|---|---|
| Whisper Large v3 | openai/whisper | $0.01 per response |
| ElevenLabs Scribe v1 | elevenlabs/scribe-v1 | $0.03 per response |
Full catalog on the models page; live per-configuration costs on the pricing page.
Call a speech-to-text model in one request
Every model shares the same request lifecycle: submit to the queue, poll the status URL, fetch the result. Swap the endpoint to switch models — nothing else changes.
cURL
curl -X POST https://queue.modelrunner.run/openai/whisper \
-H "Authorization: Key $MRUN_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "input": { "prompt": "..." } }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }Use speech-to-text models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every speech-to-text model in this table as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpFrequently asked questions
How do I transcribe an audio file via the API?
Upload the file through the Storage API (or SDK storage.upload()) to get a hosted URL, then POST it as the model’s audio input to queue.modelrunner.run. The transcription comes back in the request’s response payload.
How do I call a speech-to-text model via the API?
Every model shares the same request shape: POST https://queue.modelrunner.run/<owner>/<alias> with an Authorization: Key header and an {"input": {...}} body, then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps this in a single subscribe() call. Each model page shows copy-paste cURL, JavaScript, and Python examples with that model's real inputs.
Can I run speech-to-text models from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and every speech-to-text model in the catalog becomes a tool your AI assistant can call with the run_model tool — authorized via OAuth, no API key pasted into config.