Open-Source Speech-to-Text Models in 2026: A Voice Agent Guide
How to pick an open-source speech-to-text model for a phone agent: streaming or one sentence at a time, accuracy on phone audio, languages, licences and what fits beside your LLM on one GPU.
Read the full guide →Deep Dives in This Series
Best Speech-to-Text APIs in 2026, Tested on Voice Agent Calls
Which hosted speech-to-text APIs keep up with a caller on a phone line: stream prices, concurrency caps, accuracy on phone audio, languages, and which ones run in Dograh with your own key.
OpenAI Whisper for Voice Agents: API vs Self-Hosted, Costed
When OpenAI's Whisper API beats running Whisper on your own GPU for a voice agent, and when it doesn't: the price arithmetic, the live-call limits and the two Whisper routes that run in Dograh.
Nvidia Parakeet for Voice Agents: v2 or v3 Beside Your LLM
Nvidia Parakeet TDT 0.6B for phone agents: why it fits beside your language model on one GPU, v2 for English against v3 for 25 languages, what streaming means for each, serving it for Dograh, and CC-BY-4.0.