Releasesby GlyphFlux TTS (Early Access)
Flux TTS, Deepgram's streaming-first speech synthesis model, is now available in self-hosted deployments as an Early Access feature. Flux TTS is served on the new /v2/speak endpoint, which offers both a batch REST transport and a real-time WebSocket transport. Aura and Aura-2 continue to be served on /v1/speak and are unchanged. Flux TTS is off by default.
Also shipped Aug 12, 2026Deepgram in August 2026 →
Define business concepts with Pages (Beta)
You can now use Pages to give business terms, acronyms, and KPIs a single governed definition. Part of Unity Catalog semantics , Pages form the human-modeled layer of the Genie Ontology that Genie One draws on to ground its answers. See Pages .
Custom trace views in the MLflow trace explorer are in Beta
You can now build custom trace views in the Databricks MLflow trace explorer. Describe the layout you want in plain language, and Genie generates a reusable view that surfaces the trace fields, metrics, and feedback controls most relevant to your review workflow. See Build a custom trace view .
Google Search Console connector is available in Beta
The managed Google Search Console connector is now available in Beta in Databricks Lakeflow Connect. Use it to ingest search performance data, site metadata, and sitemap information from Google Search Console into Databricks.
Glean connector in Lakeflow Connect (Beta)
You can now ingest data from Glean into Databricks using the managed Glean connector in Lakeflow Connect. The connector ingests company-wide usage insights for search, Assistant, and agents, along with the shortcuts (go links) defined in your Glean deployment, using a Glean Client API token. This feature is in Beta . See Glean connector .
Amplitude connector (Beta)
The Amplitude connector in Lakeflow Connect is now in Beta. Ingest product analytics event data along with event, cohort, and annotation metadata from Amplitude. See Amplitude connector .
Gemini Enterprise: GitHub connector with data federation
The GitHub connector with data federation is generally available (GA) in Gemini Enterprise. The connector lets you search and act on GitHub repositories, issues, and pull requests directly from the Gemini Enterprise agent, with tool actions such as creating branches, adding issue comments, merging pull requests, and pushing files.
More from DeepgramEvery Deepgram release →
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...
FIPS 140-3 Images
FIPS 140-3 images are available for all four self-hosted services, published under the -fips tag suffix: quay.io/deepgram/self-hosted-api:release-260812-fips quay.io/deepgram/self-hosted-engine:release-260812-fips quay.io/deepgram/self-hosted-license-proxy:release-260812-fips quay.io/deepgram/self-hosted-billing:release-260812-fips These images run...
This Release Contains The Following Changes
- Flux TTS (Early Access) , Flux TTS is now available in self-hosted deployments on the new /v2/speak endpoint. See Deploying Flux TTS for setup, and the section above for details. Nepali and Punjabi Support , Nova-3 monolingual models now support Nepali ( ne ) and Punjabi ( pa , pa-IN ), in both batch and streaming. See the full announcement for details.
Numerals Support Now Available for 4 New Languages: Bulgarian, Chinese (Cantonese, Traditional), Malay, and Korean (Monolingual Models)
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.
Nova-3 Adds Armenian, Plus Improved Models for Tamil, Indonesian, and Belarusian
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.
🆕 New language
- Armenian ( hy ) , available for batch and streaming. Access it by setting model="nova-3" and language="hy" in your request.
✨ Improved models
Batch models Tamil ( ta ) Indonesian ( id ) Streaming models Tamil ( ta ) Belarusian ( be ) You do not need to change your API requests to access the improvements to existing languages; the updates are live for all users. For more details and to see the full list of supported languages, visit the Deepgram Supported Languages documentation .
Nova-3 Adds Afrikaans and Georgian, Plus Improved Models for Hungarian, Macedonian, Russian, Slovak, Slovenian, and Urdu
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.