Releasesby GlyphLlama Nemotron Super 49B Removed
The llama-nemotron-super-49B (Llama Nemotron Super 49B) model has been removed from the NVIDIA provider due to poor performance. The nemotron-3-nano-30B-A3B model remains available. See the NVIDIA models table for current options.
Also shipped Apr 29, 2026Deepgram in April 2026 →
Introducing Replit App Monitoring
Replit introduced App Monitoring for published apps, which notifies users via email if their application goes down. The Replit Agent can also be used to analyze logs and database state to identify the root cause of failures.
Create OpenRouter Accounts via CLI with Stripe Projects
Users can now create an OpenRouter account, generate an API key, and set up Stripe billing directly from the command line using Stripe Projects. This allows for automated account provisioning.
Gateway Authorization Proxy and hosted PAC files are now generally available
The Gateway Authorization Proxy and hosted PAC files are now generally available for all plan types. Authorization proxy endpoints add an identity-aware option alongside the existing source IP proxy endpoints , using Cloudflare Access authentication to verify who a user is before applying Gateway filtering , without installing the Cloudflare One Client .
Seer Agent is in open beta , ask it anything about your app
Seer Agent is now in open beta. Ask anything about what's happening in your application and get answers based on all the connected Sentry telemetry and context.
Google Gemini and Google Vertex AI models available for app building
Live on cloud Self-hosted version 3.383.0 and later Gemini 3.1 Pro (Preview) and Gemini 3.5 Flash can now be used to build apps, through both Google and Google Vertex AI. Refer to the AI models reference to see which models support app building.
ClickHouse integration
Live on cloud • All plans Public beta 3.375.0 Edge • All plans Public beta Retool now provides a native integration for ClickHouse , an open-source column-oriented database designed for real-time analytics.
More from DeepgramEvery Deepgram release →
GPT-5.5 LLM Model Support
OpenAI's GPT-5.5 model is now available as a managed LLM in the Voice Agent API. GPT-5.5 is an Advanced tier model. Set the model in your agent configuration: { "agent": { "think": { "provider": { "type": "open_ai", "model": "gpt-5.5", "temperature": 0.7 } } } } For the full list of supported models and pricing tiers, see the Voice Agent LLM Models...
Cartesia TTS Speed Control
The agent.speak.provider.speed parameter now supports Cartesia TTS in addition to Deepgram TTS. For Cartesia, the parameter accepts the following preset values: slowest slow normal fast fastest You can also pass a numerical value for more granular control. See the Cartesia speed documentation for details.
Container Images (release 260430)
- quay.io/deepgram/self-hosted-api:release-260430 Equivalent image to: quay.io/deepgram/self-hosted-api:1.185.0-2 quay.io/deepgram/self-hosted-engine:release-260430 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.116.0-1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260430 Equivalent image...
Aura-2 Speed and Pronunciation Controls require an updated voice-pack
The new Aura-2 Speed and Pronunciation Control features in this release are powered by an updated Aura-2 English voice-pack model. If your deployment is using an Aura-2 English voice-pack from before the April 2026 release (e.g., the 2025-04-15.0 version of the voice-pack), requests including the speed or pronounce parameters will return 400 Bad Request .
This Release Contains The Following Changes
- Nova-3 Gujarati , Nova-3 now supports Gujarati ( gu ) for both batch and streaming. Aura-2 Speed and Pronunciation Controls , Aura-2 TTS voices now support runtime speed and pronunciation control. See Voice Controls for details.
Aura-2 Voice Controls , Speed and Pronunciation
Aura-2 TTS voices now support runtime speed and pronunciation controls in English and Spanish, available on both batch and streaming WebSocket endpoints. Together, these controls give developers finer-grained tools to improve naturalness , tuning pacing and correcting pronunciation to match their needs.
Voice Agent
These controls are also supported when using Aura-2 inside the Voice Agent API: set speed once at the session level, and have the LLM emit pronunciation overrides inline. See Voice Agent TTS Controls for the recommended setup.
Self-Hosted
These controls are powered by an updated Aura-2 voice-pack model. Self-hosted deployments using a voice-pack from before the April 2026 release will return 400 Bad Request on requests including speed or pronounce parameters. See the April 2026 self-hosted release notes for voice-pack version requirements and upgrade instructions.