Releasesby Glyph🆕 Word-Level Timestamps Now Available in Flux
Flux now includes word-level timestamps in its responses. Each word in the words array carries start and end times (type double ) alongside the existing word and confidence values.
Also shipped Jul 2, 2026Deepgram in July 2026 →
VARIANT data type on Delta Direct tables (General availability)
With this release, Snowflake supports the VARIANT data type on Iceberg tables created from Delta table files in object storage (Delta Direct). When your Delta tables include variant columns, Snowflake maps them to the Snowflake VARIANT data type. You can query semi-structured data using VARIANT functions and dot or bracket notation.
Metadata-based sensitive data classification recommendations (Public Preview)
Snowflake is rolling out metadata-based sensitive data classification recommendations in Snowsight to help you identify databases that are likely to contain sensitive data and enable classification with one click.
Lakeflow Connect row filtering is now generally available
Row filtering in Lakeflow Connect is now generally available. Row filtering allows you to ingest only the rows you need by applying conditions similar to a SQL WHERE clause, improving performance and minimizing data duplication.
Genie One enhancements and bug fixes
- Ontology snippets (Public Preview) : Genie One now supports ontology snippets. This feature is in Public Preview. Contact your Databricks account team to sign up. See Genie Ontology . Document edit timestamps : Documents now show the date and time they were last edited. See Documents in Genie One . Links in documents : Documents now support links.
Genie Agent (formerly Genie Space) enhancements
- Agent mode is generally available : Agent mode in Genie Agents (formerly Genie Spaces) is now generally available. Agent mode uses multi-step reasoning to answer complex, exploratory questions with a report that includes citations, visualizations, and supporting tables. See Genie Agents concepts .
[Launched] Generally available: Anthropic Claude Sonnet 5 on Azure Databricks
Azure Databricks now supports Anthropic Claude Sonnet 5 through Azure Databricks AI Model Serving. Claude Sonnet 5 is Anthropic's most agentic Sonnet model to date, delivering near-Opus-level intelligence with Sonnet's cost efficiency and speed. Designed
More from DeepgramEvery Deepgram release →
SDK Compatibility
Most integrations will continue to work without changes. The exception is clients configured to reject unrecognized fields, which may return errors when the new fields appear. Here is what we recommend: Python : Versions 6.0.1 and later are unaffected. If you are on the 5.x line, update to 5.3.4.
Claude Sonnet 5 Now Available
claude-sonnet-5 is now available as a managed Anthropic LLM in the Voice Agent API. This Advanced tier model delivers improved reasoning and conversational quality for your voice agents. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "anthropic", "model": "claude-sonnet-5", "temperature": 0.5 } } } }
Deprecation: Claude Sonnet 4
claude-sonnet-4-20250514 is now deprecated. Migrate to claude-sonnet-5 or another supported Anthropic model. This model has been retired by Anthropic and will produce an error if specified in your settings configuration. For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .
Container Images (release 260630)
- quay.io/deepgram/self-hosted-api:release-260630 Equivalent image to: quay.io/deepgram/self-hosted-api:1.192.3-1 quay.io/deepgram/self-hosted-engine:release-260630 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.119.1-1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260630 Equivalent image...
Breaking Change: GET /v1/models Response Format
The self-hosted GET /v1/models endpoint now lists every loaded model, not just core speech-to-text (Nova) models. The response now also includes Text-to-Speech (Aura voice packs and voices) and helper models (entity detection/NER, diarization), groups results by model type, and indicates batch versus streaming mode for each speech-to-text model.
This Release Contains The Following Changes
- Flux Word-Level Timestamps , each word in the words array now includes start and end times on the Flux streaming endpoint ( /v2/listen ). This is an additive change. If your client library rejects unrecognized response fields, update to a current SDK version , for the Deepgram Python SDK, use 6.0.1 or later, or 5.3.4 if you are on the 5.x line.
InjectAgentMessage: behavior field and new interrupt mode
The InjectAgentMessage message now accepts a behavior field that controls how an injected message interacts with any in-progress user or agent turn. The default and queue behaviors were previously documented; the new interrupt behavior is introduced with this release. default , the agent speaks only if neither the user nor the agent is mid-turn.
Latency reporting
LatencyReport provides a detailed LLM, TTS, and end-to-end latency breakdown for each turn, including ttt_token_latency , ttt_text_latency , ttt_tool_latency , ttt_thinking_latency , tts_latency , and total_latency .