Speech to Text
Accurate, scalable transcription for any audio
Enterprise‑grade STT with diarization, timestamps, and privacy controls. Batch today, streaming on the roadmap.
Why SonarText STT
Accuracy
Accurate transcription using SOTA transcription models with punctuation and casing, even in noisy calls
Speed
Optimized for fast batch processing to deliver transcription results quickly
Diarization
Automatically identify speakers and separate transcription to simply follow conversations
Timestamps
Enable timestamps by word or segment for accurate subtitles or for searchable references
Flexibility
Use the input and output formats that work best for your application
Pricing
Industry leading pricing to support your applications
Build in Minutes
Start with curl, Node, or Python.
curl -X POST https://api.sonartext.com/v1/transcribe \
+ -H "Authorization: Bearer <API_KEY>" \
+ -F file=@audio.mp3See the API Reference for full parameters.