Releasesby GlyphDeprecation: 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 .
Also shipped Jul 1, 2026Deepgram in July 2026 →
Fivetran Context Layer is in public preview
Context Layer builds a context layer from documentation sources, systems of record and analytical sources, then connects it to an organization's AI coding and chat tools.
Fivetran sunsets the AVEVA PI and Delighted connectors
New AVEVA PI and Delighted connections are blocked from July 1, 2026. Existing AVEVA PI connections stop syncing July 23, 2026, and Delighted connections are paused after the Delighted API deprecation.
Fivetran Move a Connection REST API endpoint enters beta
A new beta endpoint moves connections from one destination group to another.
Workload identity federation for Snowflake workloads that access external services (General availability)
Snowflake can now act as the OpenID Connect (OIDC) provider when Snowflake workloads authenticate to external services. To use this capability, create a secret of type WORKLOAD_IDENTITY_FEDERATION and share its issuer URL and subject identifier with the external service to establish trust.
Veeva Vault connector (Beta)
The Veeva Vault connector is now available in Lakeflow Connect in Beta . Workspace admins can control access to this feature from the Previews page. The connector uses Veeva's Direct Data API to ingest all standard objects, custom objects, system tables, and audit trail tables from your Vault instance into Databricks.
MySQL integrated CDC pipeline is now in Beta
The integrated CDC pipeline for MySQL is now in Beta . An integrated CDC pipeline ingests change data from MySQL into Databricks using a single pipeline, combining extraction and application into one pipeline update. Unlike the standard gateway-based architecture, an integrated CDC pipeline requires no separate ingestion gateway.
More from DeepgramEvery Deepgram release →
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 } } } }
🆕 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.
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.
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.
🆕 Redaction: Expanded Language Coverage & Flux Support
- Number redaction ( numbers , true , aggressive_numbers ) now supports these languages on the Hosted API: Danish, Dutch, English, French, German, German (Swiss), Italian, Norwegian, Polish, Portuguese, Spanish, and Swedish. On multilingual models, number redaction applies the correct rules to each detected language within a transcript.
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.