
Speech and voice AI APIs
deepgram.com (opens in a new tab)Deepgram provides real-time APIs for speech-to-text, text-to-speech and production-grade voice agents, built on voice-native foundation models rather than general models adapted to audio. More than 200,000 developers and 1,300 organisations build on it, including Twilio, Cloudflare, Sierra, Decagon, Vapi, Daily, Cresta and Granola. The models are available through cloud APIs or as self-hosted and on-premises software, which matters for regulated buyers who cannot send audio off site. Deepgram has processed over 50,000 years of audio and transcribed more than a trillion words.
