Changelog

Flux TTS is Generally Available

Flux TTS, Deepgram’s conversation-native text-to-speech model, is now generally available on /v2/speak — streaming WebSocket and batch REST.

New at GA:

• Barge-in with exact spoken-text reporting. Interrupt cancels the active turn on the live socket, and SpeechInterrupted reports text_spoken and text_remaining — an exact answer to “what did the user actually hear,” so your LLM context stays correct without reconstructing it from playback timing. See Interruption Handling.
• Mid-session speed changes. Configure adjusts speed without reconnecting, answered by ConfigureSuccess / ConfigureFailure.
• speed on both transports. One of 0.85–1.15 in 0.05 increments.
• An expanded voice catalog. 36 English voices across American, British, Irish, Australian, Indian, Singaporean, and Filipino accents, led by 12 featured all-rounders. See Voices & Languages.

Also new alongside GA, but still in beta: an expressivity parameter that shifts a voice’s delivery register from -2 (calmer) to 2 (more animated) on both transports. The tuned default (0) remains the recommended, production-validated setting. See Expressivity.

Coming soon as fast follows: inline pause and pronunciation controls in Speak text — the controls_applied tallies are already reserved for them.

The GA surface is additive: /v1/speak and every Aura model string are unchanged. See the Flux TTS docs to get started, or hear the voices at talk.deepgram.com.

Flux TTS is generally available, and is now the default agent voice

Flux TTS is the default agent.speak provider

Flux TTS is generally available in the Voice Agent API. A Settings message that omits agent.speak altogether now uses Flux TTS with the flux-kit-en voice, where it previously used aura-asteria-en.

Set agent.speak.provider.version to v2 with a flux-{voice}-{language} model to select Flux TTS explicitly, or v1 with an aura-* model for Aura.

1
{
2
  "agent": {
3
    "speak": {
4
      "provider": {
5
        "type": "deepgram",
6
        "version": "v2",
7
        "model": "flux-alexis-en"
8
      }
9
    }
10
  }
11
}

The GA voice catalog is 36 English voices across seven accents. See the Flux TTS voice catalog.

Breaking: default sessions requesting compressed audio are now rejected

Flux TTS streams raw audio, so it accepts only the linear16, mulaw and alaw output encodings, with no container and no bit rate. Because it is now the default provider, a session that omits agent.speak and requests a compressed encoding (mp3, opus, flac, aac) or a container such as wav receives INVALID_SETTINGS where it previously received Aura audio.

Name an aura-* model in agent.speak to keep the previous behavior:

1
{
2
  "agent": {
3
    "speak": {
4
      "provider": {
5
        "type": "deepgram",
6
        "version": "v1",
7
        "model": "aura-asteria-en"
8
      }
9
    }
10
  },
11
  "audio": {
12
    "output": { "encoding": "mp3" }
13
  }
14
}

For the formats Flux TTS accepts, see TTS Models.

speed for Flux TTS

agent.speak.provider.speed now applies to Flux TTS. Flux TTS accepts 0.85, 0.9, 0.95, 1.0, 1.05, 1.1 or 1.15; Aura continues to accept any value from 0.7 to 1.5.

1
{
2
  "agent": {
3
    "speak": {
4
      "provider": {
5
        "type": "deepgram",
6
        "version": "v2",
7
        "model": "flux-alexis-en",
8
        "speed": 1.05
9
      }
10
    }
11
  }
12
}

For details, see TTS Models.

UpdateSpeak switches Flux TTS voices from the next turn

UpdateSpeak now changes the voice of a Flux TTS session. The new voice applies to the agent’s next turn, so a turn already being spoken finishes in the voice that started it. SpeakUpdated confirms the change will be used; an update that cannot be applied returns an Error instead.

For details, see the UpdateSpeak documentation.