Releasesby GlyphContainer Images (release 260714)
- quay.io/deepgram/self-hosted-api:release-260714 Equivalent image to: quay.io/deepgram/self-hosted-api:1.192.5-1 quay.io/deepgram/self-hosted-engine:release-260714 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.119.1-3 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260714 Equivalent image...
Also shipped Jul 14, 2026Deepgram in July 2026 →
Conversational analytics now supports the AI.AGG function
Conversational analytics now supports the AI.AGG function . This function is in Preview .
CREATE OR ALTER is generally available for 24 object types
CREATE OR ALTER is now generally available for 24 object types. CREATE OR ALTER creates an object if it doesn’t exist, or modifies an existing object to match the statement definition. It’s especially useful in declarative deployment workflows and CI/CD pipelines where the same script must be safe to re-run.
Catalog integration for Snowflake Postgres (General availability)
Catalog integrations for Snowflake Postgres are now generally available. A Snowflake Postgres catalog integration lets Snowflake automatically discover tables managed by a Snowflake Postgres instance and access them as read-only Apache Iceberg™ tables, using vended credentials so you don’t need to configure an external volume or manage storage credentials...
Allowlist partner platform IPs in context-based ingress control (Beta)
Context-based ingress control now supports Partner Platforms as a network source. Select a partner platform to allowlist the IPs that third-party apps use to connect to Databricks, including Power BI, Tableau Cloud, and dbt platform. Databricks manages and updates these IP lists automatically. See Network sources .
Trigger.AvailableNow support for OpenSharing streaming (GA)
Streaming reads from OpenSharing tables now support the Trigger.AvailableNow trigger. This trigger captures the shared table's current version when it starts, processes all available data across one or more micro-batches (honoring maxFilesPerTrigger and maxVersionsPerRpc ), and then stops, which is well suited to scheduled, batch-like incremental...
Admin API adds Claude Enterprise user management in beta
Claude Enterprise organizations can list and look up members, change roles, remove members, manage invites and groups, and read custom roles through the Admin API. Group and custom-role requests need the ce-user-management-2026-07-13 beta header.
More from DeepgramEvery Deepgram release →
This Release Contains The Following Changes
- Number and Percentage Formatting , decimal values now keep their trailing zeros, so "zero point zero zero percent" renders as 0.00% (previously 0% ); and Malay transcripts now convert spoken numbers to numerals.
Improved Models Released for Multiple Languages
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.
🆕 Improved Models
Batch models Ukrainian ( uk ) Catalan ( ca ) Turkish ( tr ) Romanian ( ro ) Finnish ( fi ) Malay ( ms ) Greek ( el ) German ( de ) Dutch ( nl ) French ( fr , fr-CA ) Streaming models Catalan ( ca ) Turkish ( tr ) Malay ( ms ) You do not need to change your API requests to access these improvements; the updates are live for all users.
🆕 Numeral Formatting for Flux
Flux now supports the numerals feature, which converts numbers from written format to numerical format (for example, "nine hundred" becomes "900"). Numerals are available on both Flux models: Flux English ( model=flux-general-en ) , full numeral formatting.
Enabling Numerals
Set numerals=true as a query parameter when you open the WebSocket connection: wss://api.deepgram.com/v2/listen?model=flux-general-en&numerals=true&encoding=linear16&sample_rate=16000 On Flux, numerals is set at connection time only and cannot be changed through the Configure message.
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 .
New Models Released for Multiple Languages
We have released new Nova-3 monolingual models for the following languages. These additions expand language coverage for both batch and streaming workloads.