Unmute
Unmute by Kyutai is an open-source voice AI platform that gives any text-based LLM the ability to listen and speak. It features low-latency speech-to-text and text-to-speech models designed for real-time conversational AI. Developers can integrate Unmute to build voice-enabled agents, assistants, and interactive applications. The modular architecture supports custom voices and languages. Unmute is particularly well-suited for applications requiring fast, natural-sounding voice interactions with minimal latency. As an open-source solution, it offers transparency and flexibility for teams building voice-first AI products.
You might also like
Related tools
Braina is a versatile AI software enabling seamless interaction with your computer through voice commands in multiple languages. With speech-to-text conversion in over 100 languages, Braina stands out as a free, user-friendly tool for local AI language model deployment on Windows systems. Supporting both CPU and GPU for local inference, including Nvidia/CUDA and AMD, Braina offers flexibility and ease of use. It excels in unlimited dictation with up to 99% accuracy, AI correction, and supports various applications and websites. With features like OpenAI API integration, dictation templates, and webpage attachment for input, Braina is a comprehensive solution for AI-driven tasks, making it an essential tool for efficient and effective computer interactions.
talat is a Mac meeting notes app that records microphone and system audio, transcribes conversations in real time, and turns meetings into searchable, editable notes without sending data to the cloud. It runs transcription on Apple’s Neural Engine and can generate summaries, decisions, and action items using a local model or a user-supplied cloud API key. talat works alongside Zoom, Teams, Google Meet, and similar conferencing tools, quietly capturing both sides of a conversation while letting users edit transcript segments, reassign speakers, and export notes afterward. It is positioned as a privacy-first alternative to cloud meeting assistants like Granola or Otter, with local storage, offline-friendly workflows, webhook support, MCP connectivity, and flexible integrations for users who want AI meeting intelligence while keeping control of their data.
Super Voice Mode is a macOS voice layer for AI-assisted development and everyday dictation. It lets users hold a hotkey, speak, and insert AI-corrected text at the cursor, while also adding a voice assistant layer for tools such as Claude, Codex, or local LLMs. The product is useful for developers, writers, and power users who want to talk through prompts, edits, commands, and notes without sending all audio to a cloud service. Its homepage emphasizes on-device operation, no account requirement, free corrected dictation, personas, voices, pricing, and a direct macOS download. The Show HN launch is timely because voice is becoming a serious interface for coding agents, not just a generic transcription feature.