Voice Agents

Sarvam + Gemini Flash

Sarvam STT/TTS with Gemini 2.0 Flash LLM

Gemini Live

Gemini native audio — direct speech-to-speech

ChatGPT Realtime

OpenAI Realtime API — direct speech-to-speech

Sarvam + GPT-4o

Sarvam STT/TTS with GPT-4o LLM