Handle single-file transcription, async jobs, batch processing, polling, and webhooks with one API built for reliable transcription at scale.
curl -X POST https://api.transcribeapi.com/v1/transcribe \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@audio.mp3" curl -X POST https://api.transcribeapi.com/v1/transcribe \
-H "Authorization: Bearer YOUR_API_KEY" \
-F "file=@audio.mp3" \
-F "language=en" \
-F "webhook_url=https://app.com/webhook" Everything you need to add transcription to your product.
One endpoint handles single files, async jobs, and batch processing. POST multipart or JSON—it just works.
Batch jobs complete in minutes, not 24 hours. Up to 10,000 files and 10 GB per batch req.
SDKs for Node.js, Python, and Cloudflare Workers. Handles uploads, polling, and retries for you.
Get results delivered to your server with signed webhooks, or poll job status. Works great with serverless.
Audio files are deleted immediately after transcription.
Every endpoint, error code, and option is documented with copy-paste examples in 7 languages.
Pay only for the audio you transcribe. No hidden fees
Billed per second, rounded up to the nearest second.
Every new account gets 60 mins of free transcription just save a card to prevent abuse. No charge.
These are maximum expected completion times.
| Audio Duration | Max Completion |
|---|---|
| Under 10 seconds | 1–4 sec |
| Under 10 minutes | Up to 25 sec |
| Single file under 1 hour | Up to 5 min |
| Single file 1–5 hours | Up to 15 min |
| Single file 5–10 hours | Up to 30 min |
Batch jobs add ~100–300 ms per file on top of the duration-based latency.
State-of-the-art speech recognition from OpenAI's Whisper family.
Optimized for speed. Delivers near real-time transcription with minimal latency—ideal for interactive applications and quick turnarounds.
Maximum accuracy for challenging audio. Handles accents, background noise, and 99 languages with exceptional precision.
Get 60 mins of free transcription.
Start Transcribing Free