Audio computing

Diktafon is a private, open-source voice memo app that transcribes and summarizes your recordings entirely on your device — organized like cassette tapes. - jaromiru/diktafon

Myna is a lightweight speech-to-text application for Ubuntu Desktop. - canonical/myna

Learn what Miso One is, how Miso TTS 8B works, where to download the open weights, and what to know before running the English-only emotive TTS model locally.

High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean. - myshell-ai/MeloTTS

Blind vote on HF TTS models!

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

OpenTTS is the leader in conversational AI and text to speech. 147+ languages and 500+ voices

Super Voice Mode is an AI voice assistant and dictation app for Mac. Talk to Claude, Codex, Gemini, Ollama, and local LLMs, or dictate in any app with Parakeet and Whisper speech recognition. On-device by default.

Record both sides of any meeting. Transcribe and summarize locally on your Mac. No cloud, no data leaving your machine.

Deezer source separation library including pretrained models. - deezer/spleeter

PersonaPlex code

Per-app volume control, local AI transcription, and professional audio routing for macOS. Native, fast, and private.

Write 3x faster with Al voice dictation that gets your intent right. Say it once, see it written as you meant.

Optimize your Linux system for low latency audio. Contribute to gaheldev/Millisecond development by creating an account on GitHub.

We introduce PersonaPlex, a full-duplex conversational AI model that enables natural conversations with customizable voices and roles. PersonaPlex handles interruptions and backchannels while maintaining any chosen persona, outperforming existing systems on conversational dynamics and task adherence.

Convert your sheet music from various image formats to digital midi for your musical workflow

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice...

The best voice-to-text app for macOS. Lightning-fast, private, and free.

Port of OpenAI's Whisper model in C/C++. Contribute to ggml-org/whisper.cpp development by creating an account on GitHub.

Explore built-in accessibility features to help you create, connect, and do what you love, your way.