Skip to main content
Try out Ink 2, which provides improved turn detection for English voice agents.

ink-whisper

Ink Whisper is our most affordable speech-to-text model. It delivers higher accuracy and lower latency than baseline Whisper. Additional capabilities compared to baseline Whisper:
  • Handles variable-length audio chunks and interruptions gracefully using dynamic chunking.
  • Reliably transcribes speech with background noise.
  • Accurately transcribes audio with telephony artifacts, accents, and disfluencies.
  • Excels at transcribing proper nouns and domain-specific terminology.
To learn how to use the Ink STT family, see Compare Endpoints.