Flux TTS

Flux TTS Overview

Flux TTS is Deepgram’s voice-agent-first, streaming-first text-to-speech family, served on /v2/speak over both a real-time WebSocket and a batch REST transport.

Flux TTS brings the Flux promise to speech synthesis: a model and API built for the realities of a voice agent pipeline, not a one-shot text-to-audio pipe. It is served on the /v2/speak endpoint and shares one set of Flux voices across two transports.

Two transports, one voice family

TransportEndpointBest for
Real-time / conversational (WebSocket)wss://api.deepgram.com/v2/speakLive voice agents: stream LLM tokens in, stream audio back, interrupt and resume across turns
Batch / pre-recorded (REST)POST https://api.deepgram.com/v2/speakPre-generating fixed audio (IVR prompts, notifications, audiobook lines) where the whole text is known up front

Not sure which to use? See Batch vs Streaming.

Why Flux TTS

  • Streaming-first — Stream LLM tokens straight into the socket; the server places flush boundaries internally.
  • Turn-based lifecycle — Each agent response is a turn with a clean start/finish, reported per turn.
  • Cross-turn voice consistency — Conversational state persists across turns, so tone carries forward. See Cross-Turn Context.

Planned for GA: interruption feedback (the server reports exactly what the user heard on barge-in) and mid-stream Configure (speed).

Start here

Real-Time Getting Started
Batch (REST) Getting Started
Batch vs Streaming
Build a Flux TTS Voice Agent
Migrating from Aura