Deepgram Voice Agent API

Voice & Multimodal

Single endpoint combining Nova-3 speech-to-text, LLM routing, Aura-2 text-to-speech, and Flux conversational STT, with mid-call language switching across 10 languages.

🌐 Visit website ↗

🔗 Similar tools

Deepgram Nova-3 + Aura-2 + Flux Multilingual

Deepgram Nova-3 provides speech-to-text in 45+ languages, with conversational STT and mid-…
Pipecat ★ 15.2k

Pipecat is an open-source framework (BSD-2-Clause) for building voice and multimodal conve…
Deepgram

Sub-300ms speech-to-text and text-to-speech APIs purpose-built for real-time voice agent p…

Platforms & APIs
Dograh ★ 5.6k

Dograh is an open-source, self-hostable voice AI platform, serving as an alternative to Va…
Cartesia

Cartesia provides ultra-low-latency voice AI designed for real-time conversational agents,…
Cartesia Sonic 3 / 3.5

Cartesia Sonic 3 / 3.5 is a state-space-model text-to-speech (TTS) system with a time-to-f…