Releasesby GlyphNova-3 Model Update
🌏 Nova-3 now supports the following new languages and language codes: Chinese (Cantonese, Traditional): zh-HK Thai: th , th-TH 🚀 Also releasing improved Nova-3 models for the following languages: Bengali ( bn ) Marathi ( mr ) Tamil ( ta ) Telugu ( te ) Access these models by setting model="nova-3" and the relevant language code in your request.
Also shipped Mar 17, 2026Deepgram in March 2026 →
Grafana Assistant in Slack is now generally available
Grafana Assistant arrives in Slack and lets you troubleshoot while on the go and with your colleagues in real-time. Grafana Assistant in Slack allows you to access the data and knowledge in Grafana Assistant in Slack. Ask about your traces, metrics, the latest deployment and how to fix high p99 latency in your search service.
Skills in Grafana Assistant are now generally available
Skills are now generally available for all Grafana Assistant users. Skills let you write runbooks, workflows, hints and context guides so that the Assistant can drill down even better in your stack. You can also associate slash commands with Skills so that /my-skill brings up your Skill and the Assistant works through it specifically.
Agents, Workers - @cloudflare/codemode v0.2.1: MCP barrel export, zero-dependency main entry point, and custom sandbox modules
The latest releases of @cloudflare/codemode ↗ add a new MCP barrel export, remove ai and zod as required peer dependencies from the main entry point, and give you more control over the sandbox.
AI Gateway - Log AI Gateway request metadata without storing payloads
AI Gateway now supports the cf-aig-collect-log-payload header, which controls whether request and response bodies are stored in logs. By default, this header is set to true and payloads are stored alongside metadata.
Security Overview - New Security Overview UI
The Security Overview has been updated to provide Application Security customers with more actionable insights and a clearer view of their security posture. Key improvements include: Criticality for all Insights : Every insight now includes a criticality rating, allowing you to prioritize the most impactful security action items first.
More from DeepgramEvery Deepgram release →
🤖 New LLM Models Support & Bug Fixes
We've added support for new LLM models in the Voice Agent API: OpenAI GPT-5.3 Instant ( gpt-5.3-chat-latest ) OpenAI GPT 5.4 ( gpt-5.4 ) Google Gemini 3.1 Flash Lite ( gemini-3.1-flash-lite-preview ) Example: { "type": "Settings", "agent": { "think": { "provider": { "type": "open_ai", "model": "gpt-5.3-chat-latest" } } } } For the full list of supported...
Container Images (release 260319)
- quay.io/deepgram/self-hosted-api:release-260319 Equivalent image to: quay.io/deepgram/self-hosted-api:1.180.1 quay.io/deepgram/self-hosted-engine:release-260319 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.114.4 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260319 Equivalent image to...
This Release Contains The Following Changes
- Flux Regression Fix , Resolves Flux support regression from the 260305 release. See Deploy Flux Model (STT) for deployment details. Nova-3 Language Expansion , New models: Thai ( th , th-TH ), Chinese Cantonese Traditional ( zh-HK ). Improved models: Bengali ( bn ), Marathi ( mr ), Tamil ( ta ), Telugu ( te ). See the full announcement for details.
Nova-3 Model Update
🎯 Nova-3 Swedish and Dutch Model Enhancements We’ve released updated Nova-3 Swedish and Nova-3 Dutch models, offering improved accuracy for both streaming and batch transcription.
Reasoning mode for OpenAI thinking models
You can now control the reasoning effort of supported OpenAI reasoning models using the new reasoning_mode parameter in the think provider configuration. This parameter maps to OpenAI's reasoning_effort and accepts low , medium , or high .
TTS speak speed (Early Access)
You can now control the speaking rate of Deepgram TTS in the Voice Agent API using the agent.speak.provider.speed parameter. This parameter accepts a float value between 0.7 and 1.5 , with 1.0 as the default.
Updated LLM models
New OpenAI models , Two new models are now available in the Standard pricing tier: gpt-5.4-nano gpt-5.4-mini Gemini 2.0 Flash deprecated , The gemini-2.0-flash model is now deprecated. We recommend migrating to gemini-2.5-flash or a newer Gemini model. See the Google models table for alternatives.
Container Images (release 260305)
- quay.io/deepgram/self-hosted-api:release-260305 Equivalent image to: quay.io/deepgram/self-hosted-api:1.179.5 quay.io/deepgram/self-hosted-engine:release-260305 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.113.2 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260305 Equivalent image to...