WebSocket Streaming
Stream audio over a persistent WebSocket connection. Real-time partial and final transcripts.
File-Based Transcription
Upload audio files via REST API. OpenAI-compatible endpoint.
In-Call Transcription
Enable transcription during live voice calls via Call Control or TeXML.
Engines and pricing
Transcription runs on 12 engines available through the Telnyx API: Deepgram, an in-house Whisper-based engine, Google, Azure, xAI, AssemblyAI, Speechmatics, Soniox, NVIDIA Parakeet, Cohere, Reson8, and Humain. No external provider account is required. Some engines run on Telnyx infrastructure and others are third-party services; see Data residency for which is which.- Compare engines and models in Models & Engines.
- Pricing varies by engine and model — see STT pricing.