Migrating from /v1/speak to Flux TTS

Flux TTS ships on a new endpoint, /v2/speak. The /v1/speak endpoint stays available and unchanged, and all Aura model strings continue to work on it — there is no aliasing, redirect, or deprecation. You migrate when you're ready to build on the streaming-first surface.

Use Flux TTS for new voice-agent work: streaming LLM output, barge-in, and multi-turn conversations where tone should carry across turns.

Stay on Aura if you're using Aura voices. Aura voices are served only on /v1/speak; Flux voices only on /v2/speak (where a flux-* model is required).

1. Change the endpoint. Point your WebSocket at /v2/speak (was /v1/speak). The Python (deepgram-sdk) and JavaScript (@deepgram/sdk) SDKs expose a speak.v2 client — see Getting Started and the template apps — or integrate against the WebSocket directly.
2. Keep your Speak messages. The Speak shape is unchanged. Do not specify speech_id — the server assigns it and returns it for debuggability.
3. Require a model. model is required on every /v2/speak connection. Use a Flux TTS voice string (e.g. flux-haley-en); Aura voices are served by /v1/speak, not /v2/speak.
4. Replace Clear with Interrupt. End each turn with Flush; on barge-in, send Interrupt and use the returned text_spoken / text_remaining to reconcile your LLM context — see Interruption Handling.
5. Treat Flush as end-of-turn, and read SpeechMetadata. Flush marks the end of a turn (there's no separate Finalize). The turn's SpeechMetadata reports billing and timing — use it as your end-of-turn signal (not Flushed), and drop any client-side character-count or audio-duration tracking.
6. Drop the flush toggles. The v1 flush_send-style toggles don't exist on v2 — audio starts streaming for a turn on its own, and you Flush only to mark the end of the turn.
7. Drop reconnect-to-reset logic. Prosody carries across turns automatically; there's no reset step to port.
8. Insert whitespace between distinct LLM responses. The server doesn't add whitespace between Speak messages — see Text handling.

The /v2/speak column mixes messages you send (Speak, Flush, Close) with messages the server sends back (Connected, Flushed, SpeechMetadata, SessionMetadata). See Client Messages and Server Messages for the full split.

• The Speak message shape is unchanged from v1.
• 1-hour max session duration carries over from v1. New on v2: a 60s inactivity timeout (NET-0004) — send a WebSocket Ping (or Pong) to keep long-idle sessions alive.

Markup handling carries its own warning codes, and inline pause and pronunciation controls are coming soon — see Markup handling and the warning codes.

• Getting Started with Flux TTS — connect and send your first turn
• Client Messages / Server Messages — full wire reference
• The Speech Lifecycle — the turn model that replaces v1's buffer model
• Aura (/v1/speak) docs — the endpoint you're migrating from