Releasesby GlyphThis Release Contains The Following Changes
- Nova-3 Supports 12 New Languages , Belarusian (be), Bengali (bn), Bosnian (bs), Croatian (hr), Kannada (kn), Macedonian (mk), Marathi (mr), Serbian (sr), Slovenian (sl), Tamil (ta), Tagalog (tl), and Telugu (te). Note that Arabic support is not included in this release. See the full announcement for details.
Also shipped Jan 29, 2026Deepgram in January 2026 →
Your logs' final destination is in GA. You always end up here anyway
PostHog Logs is now generally available, providing a centralized destination for logs alongside errors, session replays, and product data.
- DuckDB 1.4.4: MotherDuck supports DuckDB 1.4.4, a bugfix release
- DuckDB 1.4.4: MotherDuck supports DuckDB 1.4.4, a bugfix release. Learn more in the official DuckDB Labs 1.4.4 announcement and changelog .
Agent Runners improvements
Here are some Agent Runners improvements that all people with Credit-based pricing plans can enjoy: Shareable agent run links You can now link directly to an agent run to share it with your team or bookmark for later review.
Time in status
Time spent in individual statuses is now tracked and available throughout Linear. Hover over any issue's status indicator to see the cumulative time it's spent in each status. You can use this to spot where things are getting stuck, identify bottlenecks, and optimize your development process.
Bun v1.3.8
Fixes 8 issues (addressing 6 👍). Bun.markdown is a builtin CommonMark-compliant Markdown parser written in Zig. Bun's bundler gets bun build --metafile-md to write LLM-friendly module graph metadata. Fixes a regression in 'npm install -g bun' on Windows.
Discouraging use of `receiptJson` on `OrderTransaction` in the GraphQL Admin API
We’re discouraging use of OrderTransaction.receiptJson . You should stop relying on receiptJson in production apps. receiptJson is gateway-defined , inconsistently shaped , and may change without notice . Because its structure isn’t stable or typed, changes can lead to unexpected app failures.
More from DeepgramEvery Deepgram release →
Container Images (release 260129)
- quay.io/deepgram/self-hosted-api:release-260129 Equivalent image to: quay.io/deepgram/self-hosted-api:1.177.3 quay.io/deepgram/self-hosted-engine:release-260129 Equivalent image to: quay.io/deepgram/self-hosted-engine:3.107.0-1 Minimum required NVIDIA driver version: >=570.172.08 quay.io/deepgram/self-hosted-license-proxy:release-260129 Equivalent image...
Nova-3 Model Update
🌐 Nova-3 Now Supports Arabic and all major Arabic dialects We're excited to announce the release of the Nova-3 Arabic monolingual model , which now brings industry-leading speech-to-text support for Arabic and its major dialects!
Nova-3 Model Update
🌐 Nova-3 Adds Support for Hebrew, Farsi, and Urdu We're excited to announce the release of new Nova-3 monolingual models for Hebrew , Farsi , and Urdu ! These additions bring industry-leading speech-to-text capabilities for users of these languages.
Nova-3 Multilingual Model Update
🌍 Nova-3 Multilingual Improvements We’ve released an updated Nova-3 multilingual model , delivering accuracy improvements across supported languages , with the largest gains in code-switching scenarios .
🤖 New OpenAI & Gemini LLM Models Support
We've added support for new LLM models in our Voice Agent API! Available Models: OpenAI GPT 5.2 Instant (gpt-5.2-instant) OpenAI GPT 5.2 Thinking (gpt-5.2) Google Gemini 3 Flash (gemini-3-flash-preview) Implementation: Configure your chosen model in your Voice Agent settings: { "type": "Settings", "agent": { "think": { "provider": { "type": "open_ai"...
Nova-3 Model Update
🌐 Nova-3 supports 12 new languages We're pleased to announce the addition of 12 new languages for Nova-3 monolingual models. This expansion makes Nova-3 even more versatile and accessible for global users.
New Default Concurrency Limits
We're increasing default concurrency limits by up to 3X for Streaming Speech to Text , Text to Speech , and Voice Agent for Pay as you Go, Growth, and Enterprise plans. For full details on the rate limits for your plan, see the API Rate Limits documentation.
Multiple LLM Provider Support
We've added new functionality that allows users to specify multiple LLM providers for your Voice Agent, ensuring your agent will automatically fallback to another provider should you experience any issues. The think object supports both a single provider and an array of providers. LLM providers will be used in the order that you specify them.