Speech-to-speech systems hear and reply in voice within one model, cutting the delay and information loss of chaining ASR, an LLM, and TTS. Realtime APIs and Gemini Live use this approach to make voice agents feel responsive and lifelike.
Definition
Models that take spoken input and return spoken output directly, skipping a separate text step. Enables fast, natural voice conversation.
Speech-to-speech systems hear and reply in voice within one model, cutting the delay and information loss of chaining ASR, an LLM, and TTS. Realtime APIs and Gemini Live use this approach to make voice agents feel responsive and lifelike.
Also known as
S2S, voice-to-voice
Specialist software house for video, real-time and AI products. Founded 2005. 50 in-house engineers.
