Voice and audio

Transcribe, dictate, clone or generate speech. Open repos from GitHub and models from Hugging Face, most starred first.

Only what makers tagged for a system: macOS · Windows · Linux

Voice and audioRepo

amical

🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open source models, works offline, fast and accurate.

  • 1.6k
  • TypeScript
  • MIT
  • 5 d ago
amicalhqTake it
Voice and audioRepo

minutes

Open-source, local-first Granola/Otter alternative that Claude Code, Codex, Cursor, and any MCP client can query. Meetings, calls, and voice memos transcribed on-device into markdown you own.

  • 1.6k
  • Rust
  • MIT
  • 11 h ago
silversteinTake it
Voice and audioRepo

TTS-Audio-Suite

A ComfyUI custom node integration for local multi-engine multi-language Text-to-Speech and Voice Conversion. Supports: RVC, Echo-TTS, Qwen3-TTS, Cozy Voice 3, Step Audio EditX, IndexTTS-2, Chatterbox (classic and multilingual), F5-TTS, Higgs Audio 2, 3, and VibeVoice with unlimited text length, SRT timing, Character support, and many audio tools

  • 1.3k
  • Python
  • 4 d ago
diodiogodTake it
AI agentsRepo

agent-plugin

AI video editor for agents. ChatCut plugin and MCP server for Codex, ChatGPT, Claude Code, Cursor, Grok, Gemini CLI, WorkBuddy, Doubao Work and Qwen Work: edit your own footage by chatting, add captions and subtitles, remove silences and filler words, create motion graphics, and export an editable timeline.

  • 1.1k
  • JavaScript
  • Apache-2.0
  • 20 h ago
ChatCut-IncTake it
Voice and audioRepo

CloneTTS

A lightweight, offline Android Text-to-Speech (TTS) engine enabling seamless system-wide voice cloning and high-fidelity text reading. / 运行在安卓本地的轻量级文字转语音 (TTS) 引擎,支持离线发音人提取、零门槛音色克隆与双擎系统级全局听书。

  • 900
  • 5 d ago
sipeterTake it
Hardware and DIYRepo

sanoTTS

sanoTTS (सानो = 'small' in Nepali): 294k–2.27M-parameter neural TTS that runs on a $3 chip, in the browser, or in Python with low-latency streaming.

  • 848
  • C
  • GPL-3.0
  • 3 d ago
AmpixaTake it
Voice and audioRepo

vui

Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.

  • 782
  • Python
  • 6 wk ago
fluxions-aiTake it

Send to which agent?

goes to the agent you pick.

Get , open it once and sign in. Then come back here and press the button again.