Releasesby Glyph🆕 Improved Nova-3 Medical Batch Model Released
We’ve released an upgraded Nova-3 Medical batch model with improved medical term recognition. Key Improvements: Expands the model’s medical vocabulary with new medical terms Boosts medical term recognition to 97.20% KRR Maintains WER parity with no observed regression on common or conversational terms
Also shipped May 29, 2026Deepgram in May 2026 →
Guardrails: Protect your Agents, Data, and Costs
OpenRouter has introduced configurable security and governance tools, including budget enforcement, zero data retention, and prompt injection defense.
What's new in Sigma
AI Support for Amazon Bedrock AI provider (Beta) Amazon Bedrock is now a supported AI provider, letting you use Anthropic foundation models with Sigma AI-powered features. For setup instructions, see Add Amazon Bedrock as an AI provider . Admin Connect to ClickHouse (Beta) Sigma now supports connections to ClickHouse.
Cloudflare One Client for macOS (version 2026.5.1155.1)
A new Beta release for the macOS Cloudflare One Client is now available on the beta releases downloads page . This release introduces the new Cloudflare One Client UI for macOS! You can expect a cleaner and more intuitive design as well as easier access to common actions and information.
Cloudflare One Client for Windows (version 2026.5.1155.1)
A new Beta release for the Windows Cloudflare One Client is now available on the beta releases downloads page . This release introduces the new Cloudflare One Client UI for Windows! You can expect a cleaner and more intuitive design as well as easier access to common actions and information.
Agents - Share sandbox previews through Cloudflare Tunnel
Sandboxes can expose a service running inside the container on a public preview URL through the sandbox.tunnels namespace. The SDK uses cloudflared inside the sandbox so you can share a running service without configuring exposePort() or a custom domain.
Neon is building the backend for apps and agents, and more release - May 29, 2026
Neon is building the backend for apps and agents. We're excited to announce that Neon is building a complete backend for apps and agents. Three new services are...
More from DeepgramEvery Deepgram release →
Container Images (release 260528)
- quay.io/deepgram/self-hosted-api:release-260528 Equivalent image to: quay.io/deepgram/self-hosted-api:1.188.1 quay.io/deepgram/self-hosted-engine:release-260528 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.117.0 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260528 Equivalent image to...
Preparation for a future Engine container change
The official Helm chart ( 0.37.0 and later) and the Docker and Podman compose files in deepgram/self-hosted-resources now set NVIDIA_VISIBLE_DEVICES=all and NVIDIA_DRIVER_CAPABILITIES=compute,utility on the Engine container.
This Release Contains The Following Changes
- Profanity Filtering for STT Multilingual , profanity_filter=true now masks recognized profanity in STT multilingual transcripts ( language=multi ). See Profanity Filtering for the supported language list and usage.
Gemini 3.5 Flash Now Available
gemini-3.5-flash is now available as a managed Google LLM in the Voice Agent API. This Standard tier model brings improved performance and efficiency to your voice agents. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.5-flash", "temperature": 0.5 } } } }
Deprecation Notice
The Gemini 2.5 Flash family of models is deprecating in October. Start testing newer models now to ensure a smooth migration. For more details on Gemini model deprecations, see Google's Gemini deprecations page . For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .
🆕 Profanity Filtering for Multilingual Models
Deepgram’s Profanity Filtering feature is now available for all multilingual models: Nova-2 multilingual , Nova-3 multilingual , and Flux multilingual ( language=multi ). You can enable profanity filtering in your API requests by setting the profanity_filter=true parameter.
🛠️ Fix: Improved Word Spacing in Korean Transcripts
We fixed an issue affecting Korean transcripts ( ko , ko-KR ) where word spacing was sometimes missing. Transcripts should now better reflect proper Korean spacing, improving readability for users working with Korean audio. See the full list of supported languages on the Models & Languages Overview page .
Gemini 3.1 Flash Lite Now Available
gemini-3.1-flash-lite is now available as a managed Google LLM in the Voice Agent API. This Standard tier model replaces the preview version. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "google", "model": "gemini-3.1-flash-lite", "temperature": 0.5 } } } }