transcribe.so API · v1
Speech-to-text as a Bearer token.
Same engine that powers transcribe.so, accessed through a single HTTP endpoint. One API key, per-minute pricing, no setup. Built for scripts, pipelines, and anything you'd rather not paste files into a browser for.
Send your first request
Three lines of glue. Drops directly into a script, a Cloudflare Worker, or n8n.
curl -X POST https://transcribe.so/api/v1/transcriptions \
-H "Authorization: Bearer tsk_live_REPLACE_ME" \
-H "Content-Type: application/json" \
-d '{
"source": "external_url",
"url": "https://example.com/podcast.mp3",
"pipeline_code": "qwen3-asr-flash-filetrans",
"language": "auto"
}'
# Then poll until status === "completed":
curl https://transcribe.so/api/v1/transcriptions/tr_4821 \
-H "Authorization: Bearer tsk_live_REPLACE_ME"Pricing
Same per-minute rates as the dashboard. Billed against your wallet — monthly credit first, then top-up balance. No separate API quota, no surprise minimums.
| Model | Pipeline code | Per minute | Per hour |
|---|---|---|---|
| GPT-4o Transcribe (timestamps + diarization) + AI analysis | gpt-4o-transcribe-diarize | $0.0647 | $3.88 |
| Qwen3-ASR-Flash-Filetrans (timestamps) + AI analysis | qwen3-asr-flash-filetrans | $0.0285 | $1.71 |
| Voxtral Mini Transcribe with Diarization + AI Analysis | voxtral-mini-transcribe | $0.0296 | $1.78 |
Bearer auth, nothing else
One header. No cookies, no CSRF, no SDK. curl works.
Same wallet as the dashboard
Monthly credit first, then top-up. Spend tracked per key for visibility — revoke one if it goes rogue, the rest keep working.
Idempotent POSTs
Send the same Idempotency-Key twice and you get the same response twice. Retries are safe.
Async with polling
Submit, get a transcription ID, poll GET /transcriptions/:id until it's done. Webhooks coming next.
Multilingual + diarization
Whisper, Qwen3-ASR-Flash, Voxtral, GPT-4o-transcribe-diarize. Pick the model per request — the same ones you use in the dashboard.
Resumable uploads soon
v1 ships with external-URL transcription. Direct file uploads via a presigned S3 URL land in the next release.
Ready to ship?
Create a key, paste it into your script, and you're transcribing inside a minute. We'll keep your wallet topped up; you keep the audio flowing.