ElevenLabs produces natural speech and clones voices from a short sample, but every character goes through a paid API. These projects do text-to-speech, and often voice cloning, locally, so audio and reference voices never leave your machine.
Quality, speed and language coverage differ more than star counts suggest. Small models run in real time on a laptop CPU; the most expressive ones need a recent GPU. Check each license before using a cloned voice commercially.
Updated 7 min ago
70% health, 30% momentum. Projects younger than 12 months, or too new to assess, are listed under Rising newcomers while they gain stars.
Ranked by health, then momentum
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
Fast and local neural text-to-speech engine
Native speech-to-text for Linux - Fast, accurate, private, and hackable system-wide dictation
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
🧠 Leon is your open-source personal assistant.
SOTA Open Source TTS
AI Agent Engineering Platform built on an Open Source TypeScript AI Agent Framework
Open-source State-of-the-art TTS model which runs on a CPU 😻
A nearly-live implementation of OpenAI's Whisper.
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
On-device Speech AI for Apple Silicon
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.
SoTA open-source TTS
https://hf.co/hexgrad/Kokoro-82M
A generative speech model for daily dialogue.
Instant voice cloning by MIT and MyShell. Audio foundation model.
An awesome browser extension that reads aloud webpage content with one click
A TTS model capable of generating ultra-realistic dialogue in one pass.
🔊 Text-Prompted Generative Audio Model
Showing 10 of 25 ranked repos. 20 newcomers are listed separately.
Under 12 months old, or too new to assess, and gaining stars.
The truly free, open-source, local-first, cross-platform CapCut replacement. Scriptable through a JSON-RPC API & MCP.
The open-source AI voice studio. Clone, dictate, create.
High-Quality Voice Cloning TTS for 600+ Languages
Open-source local AI audio & music studio for macOS & Windows. TTS, voice cloning, songs with lyrics, and multi-track scores — 100% offline, zero API fees.
Claudemy: an open-source alternative to Udemy and Coursera. Give Claude a topic, it researches the web and builds a course of 2-minute audio lessons with cited sources. A free Claude Code skill.
SOTA-Class TTS at Compact Scale
Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.
和《偶像大师 闪耀色彩》偶像实时语音/文字对话的 AI 分身：日语原声 + 中文字幕、回忆原作剧情、跨角色共享记忆；支持 Google/GitHub 登录与自带密钥，Docker Compose 一键部署（参考 LAPLACE Eidolon）
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 cloning.
Self-hosted voice agent platform: import your Dialogflow CX and CX Agent Studio agents, build and test them, and take calls on your own hardware. 20 model providers, phone and SIP through jambonz.
Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR, ReazonSpeech, parakeet and Silero VAD on Metal, Vulkan and the CPU, with an OpenAI-compatible server and live transcription.
An open-source, cross-platform ebook and PDF reader.
Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 48kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng Việt • TTS tiếng Việt
A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation
VoiceStudio 中文版：开源、完全本地的 ElevenLabs 替代品——语音克隆、语音设计、视频配音、听写、转写与有声书，646 种语言（译自 debpalash/VoiceStudio，AGPL-3.0）
AuK: An Open-Source Foundational Model for Speech Generation and Editing
Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.
A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transformer architectures (CTC/Seq2Seq), fine-tuning, and real-world pipelines like voice assistants and meeting transcription. Bilingual (EN/FA).
