Releasesby GlyphTransform How You Work: Real-Time Voice, Seamless Context, Full Command
We’re thrilled to announce Saga Web , the browser-based version of Saga, designed for instant, hands-free productivity. Whether you’re a longtime Saga power user or just getting started, Saga Web lets you: Dictate and see your words appear with real-time speech-to-text.
Also shipped Nov 14, 2025Deepgram in November 2025 →
Data masking, Read-Only mode for MCP Server, branch auto-deletion, and more release - Nov 14, 2025
Data masking (Beta) Neon now offers a data masking feature that makes it easy to create anonymized branches for development and testing. Define masking rules th...
What's new in Sigma
Admin Audit log support for GCP KSA region Sigma now supports audit log events for organizations hosted in the GCP KSA (ME Central 2) region. For a list of all supported regions, see Enable or disable audit logging .
- DuckDB 1.4.2: MotherDuck supports DuckDB 1.4.2, a bugfix release
- DuckDB 1.4.2: MotherDuck supports DuckDB 1.4.2, a bugfix release. Learn more in the official DuckDB Labs 1.4.2 announcement and changelog . Full command menu now at Cmd/Ctrl+K : Access common MotherDuck UI actions from your keyboard, including generating query edits, adding notebook cells, creating notebooks, and navigating between pages.
Access - Generate Cloudflare Access SSH certificate authority (CA) directly from the Cloudflare dashboard
SSH with Cloudflare Access for Infrastructure allows you to use short-lived SSH certificates to eliminate SSH key management and reduce security risks associated with lost or stolen keys. Previously, users had to generate this certificate by using the Cloudflare API ↗ directly.
CASB - New SaaS Security weekly digests with API CASB
You can now stay on top of your SaaS security posture with the new CASB Weekly Digest notification. This opt-in email digest is delivered to your inbox every Monday morning and provides a high-level summary of your organization's Cloudflare API CASB findings from the previous week.
More from DeepgramEvery Deepgram release →
Use Deepgram's Managed Cartesia TTS Models
We're excited to announce an easier way to use Cartesia's Text-to-Speech models inside Deepgram's voice agent – Deepgram-managed Cartesia models . Similar to our managed LLM's , simply specify Cartesia as your model provider and the correct model name to get started instantly.
🤖 Claude Haiku 4.5 LLM Support
We've added support for Anthropic's new Claude Haiku model in our Voice Agent API! Implementation: Configure your chosen model in your Voice Agent settings: { "type": "Settings", "agent": { "think": { "provider": { "type": "anthropic", "model": "claude-haiku-4-5" } } } } For complete information about supported LLMs including Claude Haiku 4.5, visit our...
Container Images (release 251118)
- quay.io/deepgram/self-hosted-api:release-251118 Equivalent image to: quay.io/deepgram/self-hosted-api:1.169.0 quay.io/deepgram/self-hosted-engine:release-251118 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.104.10 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-251118 Equivalent image...
This Release Contains The Following Changes
- Expands Nova-3 Monolingual Language Support , Nova-3 now supports 21 additional languages, bringing stronger accuracy and contextual understanding across: Eastern Europe and Eurasia : Bulgarian (bg), Czech (cs), Greek (el), Hungarian (hu), Polish (pl), Romanian (ro), Russian (ru), Slovak (sk), Ukrainian (uk) Nordics and Baltics : Estonian (et), Finnish...
Entity Detection Now Available for Streaming Speech-to-Text
We're excited to announce that Entity Detection is now available for streaming (real-time) speech-to-text with Nova 3, Nova 2, Nova, and Enhanced models. detect_entities=true Previously available only for pre-recorded audio, you can now identify and extract over 50 unique entity types in real-time streaming transcriptions, including email addresses, names...
Expanded Language Detection: Now Supports 35 Languages for Pre-Recorded Audio
Language Detection for pre-recorded (batch) audio now supports 35 languages (previously 16), allowing you to automatically detect and transcribe a much broader array of languages with one request. Enable broader coverage by setting detect_language=true in your API call.
Legacy Intelligence Features Deprecated
We have deprecated several legacy Intelligence feature parameters. As of today, requests using these legacy parameters will return HTTP 400 errors. Please update your implementation to use the current parameters.
Documentation Resources
- Sentiment Analysis Topic Detection Summarization For questions or support, please reach out through our developer support channels.