The project is MIT-licensed and community-driven, with one-click local model setup and a free cloud fallback for lower-spec machines. Mobile apps, meeting transcription, and MCP integration are on the roadmap. Full scoop
@testingcatalog
-
Amical launches an open-source AI dictation app
By
–
Amical launched a new open-source AI dictation app, reinforcing its position as a local-first alternative to subscription tools like Wispr Flow and Granola.
— 🚨 AI News | TestingCatalog (@testingcatalog) 18 février 2026
It runs entirely on your machine and includes context-aware formatting.
It uses Whisper and open-source LLMs to… pic.twitter.com/esmsX2NEa5Amical launched a new open-source AI dictation app, reinforcing its position as a local-first alternative to subscription tools like Wispr Flow and Granola. It runs entirely on your machine and includes context-aware formatting. It uses Whisper and open-source LLMs to
-
Users can submit contracts for GPT-5.2-Codex evaluation
By
–
Users can already submit their contract to be evaluated by GPT-5.2-Codex over here https://
paradigm.xyz/evmbench -
OpenAI and Paradigm launch an EVMbench to evaluate AI agents
By
–
OpenAI and @paradigm introduced a new EVMbench to measure how AI agents can detect, exploit and fix vulnerabilities in smart contracts.
-
Google launches Lyria 3 and Gemini Music to generate music
By
–
Google released Lyria 3, a new music generation model that powers the newly released Gemini Music feature. Up to 30-second music tracks are supported.
— 🚨 AI News | TestingCatalog (@testingcatalog) 18 février 2026
"The latest music generation model, which you can use to turn your ideas into musical tracks through prompts or even photos." https://t.co/6ZMO8pHeQb pic.twitter.com/rRMDctr7gWGoogle released Lyria 3, a new music generation model that powers the newly released Gemini Music feature. Up to 30-second music tracks are supported. "The latest music generation model, which you can use to turn your ideas into musical tracks through prompts or even photos."
-
Google lance un outil de génération musicale sur Gemini
By
–
BREAKING : Google started rolling out Music generation tool on Gemini. Available on one out of 5 accounts for me atm. Did you get it too?
-
PolyAI lance Agent Studio Lite pour créer des agents vocaux
By
–
PolyAI built Agent Studio Lite to make it easy for businesses to build their own AI voice agents from a single website URL.
— 🚨 AI News | TestingCatalog (@testingcatalog) 18 février 2026
These voice agents can be reused across different channels and integrated with other tech stacks. Users can rely on the PolyAI Raven voice model or connect… https://t.co/PA8tj0r9K0 pic.twitter.com/hq3YW0F7LCPolyAI built Agent Studio Lite to make it easy for businesses to build their own AI voice agents from a single website URL. These voice agents can be reused across different channels and integrated with other tech stacks. Users can rely on the PolyAI Raven voice model or connect
-
@testingcatalog — 2026-02-18
By
–
MyClaw agent provides execution through cross-app and system control, plus workflow automation for end-to-end tasks, running workflows across apps, files, browser flows, and system operations within your dedicated environment. Test it out for yourself
-
@testingcatalog — 2026-02-17
By
–
Control browser on Comet is now powered by the recently released Claude Sonnet 4.6 model on Perplexity Pro accounts.