Releasesby GlyphNova-3 Model Update
🌏 Nova-3 now supports Gujarati with the following language codes: Gujarati: gu , gu-IN Access this model by setting model="nova-3" and the relevant language code in your request. Learn more about Nova-3 and supported languages on the Models and Language Overview page.
Also shipped Apr 23, 2026Deepgram in April 2026 →
Aperture
Use Aperture ( beta ) to secure and manage your LLM agents with a single control plane across all your providers and models. New: Create custom guardrails with pre-LLM-call hooks to strip or block PII and restrict specific agent tools before requests reach the LLM.
Plan Access Tokens (PLANTs) are now in beta
Plan Access Tokens (PLANTs) are now in beta , a new authentication method for server-to-server integrations and internal automation.
FOCUS: Standardized Cost and Usage Data
Access and analyze Grafana Cloud cost and usage data using the open FOCUS standard We’re excited to announce the general availability of FOCUS support in the Cost Management and Billing app! FOCUS (FinOps Open Cost and Usage Specification) is an open industry standard for cloud cost and usage data.
NeMo NVIDIA Neural Modules 2.7.3
Highlights This release addresses known security issues. For the latest NVIDIA Vulnerability Disclosure Information visit https://www.nvidia.com/en-us/security/ , for acknowledgement please reach out to the NVIDIA PSIRT team at PSIRT@nvidia.com Uncategorized: Changelog beep boop 🤖: Bumping nemo to v2.7.3 by @nemo-automation-bot[bot] :: PR: #15552 remove...
Weights & Biases 0.26.1
Added Api methods returning artifacts, registries, automations, and related paginators now accept an optional start argument to resume iteration from a saved cursor ( @tonyyli-wandb in #11651 ) The stop_fn setting to customize how a run is stopped ( @timoffex in #11773 ) Allows overriding the default of sending a SIGINT to the Python process Changed Unified...
Access - AAGUID restrictions and AMR matching for Access independent MFA
Independent MFA in Cloudflare Access now supports two additional organization-level controls: Restrict authenticators by AAGUID , Limit enrollment to a specific set of WebAuthn authenticators using their AAGUID ↗ . This is useful for organizations that require FIPS-validated security keys or company-issued hardware.
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...
Llama 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.
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.
Container Images (release 260416)
- quay.io/deepgram/self-hosted-api:release-260416 Equivalent image to: quay.io/deepgram/self-hosted-api:1.181.7 quay.io/deepgram/self-hosted-engine:release-260416 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.115.1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260416 Equivalent image to...
This Release Contains The Following Changes
- Flux Multilingual , Real-time multilingual conversational STT is now available for self-hosted deployments. Supports 10 languages (English, Spanish, French, German, Hindi, Russian, Portuguese, Japanese, Italian, and Dutch) with code-switching support.