Changelog

Flux now gives you full control over how turns end. Beyond Flux’s native end-of-turn detection, you can override it, suppress it entirely, or blend the two — and switch between these modes on the fly, even for a single turn, with a Configure message. Turn-taking goes from a fixed behavior to something you shape around each moment of a conversation.

We have released improved Nova-3 monolingual models for ten existing languages. These updates enhance transcription quality for batch and streaming workloads.

We have added Assamese, Mongolian, and Pashto as new Nova-3 languages and released improved Nova-3 monolingual models for several existing languages. These updates expand language coverage and enhance transcription quality for batch and streaming workloads.

Deepgram Self-Hosted August 2026 Release (260826)

Container Images (release 260826)

• quay.io/deepgram/self-hosted-api:release-260826

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-api:1.192.31

• quay.io/deepgram/self-hosted-engine:release-260826

  • Equivalent image to:

    • quay.io/deepgram/self-hosted-engine:3.128.0

  • Minimum required NVIDIA driver version: >=570.172.08

• quay.io/deepgram/self-hosted-license-proxy:release-260826

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-license-proxy:1.11.0-1

• quay.io/deepgram/self-hosted-billing:release-260826

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-billing:1.14.0-1

You can now end the current user turn from your own signal instead of waiting for end-of-turn detection.

Deepgram CLI 0.3.0 is now available. It completes CLI support for Flux TTS, which reached general availability on 12 August, fixes Flux STT streaming, and enforces the CLI’s exit-code contract.

Upgrading from 0.2.26 picks up everything in this release. 0.2.27 was tagged but never published, so its changes arrive here.

expressivity for Flux TTS

agent.speak.provider.expressivity shifts a Flux TTS voice’s delivery register along a calm to animated axis. It accepts the whole numbers -2 to 2 and defaults to 0, the voice’s tuned delivery. Negative values produce calmer, steadier delivery; positive values produce more animated delivery with a wider pitch range. Every Flux voice supports it, and the value applies for the whole session.

We have added Afrikaans and Georgian as new Nova-3 languages and released improved Nova-3 monolingual models for several existing languages. These updates expand language coverage and enhance transcription quality for batch and streaming workloads.

Supported languages and language codes:

• Bulgarian (bg)
• Chinese (Cantonese, Traditional) (zh-HK)
• Malay (ms)
• Korean (ko, ko-KR)

You can now use Deepgram’s Numerals feature with monolingual models for Bulgarian, Chinese (Cantonese, Traditional), Malay, and Korean. Numerals converts spoken numbers into digits (for example, “three hundred” → “300”) in your transcript, helping you create more accurate and easily processed results.

Deepgram Self-Hosted August 2026 Release (260812)

Container Images (release 260812)

• quay.io/deepgram/self-hosted-api:release-260812

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-api:1.192.25

• quay.io/deepgram/self-hosted-engine:release-260812

  • Equivalent image to:

    • quay.io/deepgram/self-hosted-engine:3.127.0

  • Minimum required NVIDIA driver version: >=570.172.08

• quay.io/deepgram/self-hosted-license-proxy:release-260812

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-license-proxy:1.11.0

• quay.io/deepgram/self-hosted-billing:release-260812

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-billing:1.14.0

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.

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.

We have added Armenian as a new Nova-3 language and released improved Nova-3 monolingual models for several existing languages. These updates expand language coverage and enhance transcription quality for both batch and streaming workloads.

We have released improved Nova-3 monolingual models for the following languages. These updates enhance transcription quality and accuracy for both batch and streaming workloads.

🌏 Nova-3 monolingual models now support Punjabi and Nepali with the following language codes:

• Punjabi: pa, pa-IN
• Nepali: ne

Batch and streaming models are both available for these languages.

Access this model by setting model="nova-3" and the relevant language code in your request.

We have released improved Nova-3 monolingual models for the following languages. These updates enhance transcription quality and accuracy for both batch and streaming workloads.

UpdateListen: switch model and language mid-session

UpdateListen now accepts model and language changes, so you can switch speech-to-text models and languages without restarting the session. Previously the provider identity had to match the current session.

1
{
2
  "type": "UpdateListen",
3
  "listen": {
4
    "provider": {
5
      "type": "deepgram",
6
      "version": "v1",

Deepgram Self-Hosted July 2026 Release (260728)

Container Images (release 260728)

• quay.io/deepgram/self-hosted-api:release-260728

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-api:1.192.12-1

• quay.io/deepgram/self-hosted-engine:release-260728

  • Equivalent image to:

    • quay.io/deepgram/self-hosted-engine:3.123.0-1

  • Minimum required NVIDIA driver version: >=570.172.08

• quay.io/deepgram/self-hosted-license-proxy:release-260728

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-license-proxy:1.10.3

• quay.io/deepgram/self-hosted-billing:release-260728

  • Equivalent image to:
    • quay.io/deepgram/self-hosted-billing:1.13.2

The Flux numerals feature is now available in the JavaScript, Python, and Java SDKs. Set numerals=true when you open a Flux WebSocket connection to convert spoken numbers into their numerical format (for example, “nine hundred” becomes “900”). On Flux, numerals is set at connection time only and cannot be changed through the Configure message.

We have released new Nova-3 monolingual models for the following languages. These additions expand language coverage for both batch and streaming workloads.