ElevenLabs produit une voix naturelle et clone une voix à partir d’un court extrait, mais chaque caractère passe par une API payante. Ces projets font de la synthèse vocale, et souvent du clonage de voix, en local : l’audio et les voix de référence ne quittent jamais votre machine.
Qualité, vitesse et langues couvertes varient davantage que le nombre d’étoiles ne le laisse penser. Les petits modèles tournent en temps réel sur le processeur d’un portable ; les plus expressifs demandent un GPU récent. Vérifiez la licence de chaque projet avant d’utiliser une voix clonée à des fins commerciales.
70 % santé, 30 % dynamique. Les projets de moins de 12 mois, ou trop récents pour être évalués, figurent parmi les jeunes projets en hausse tant qu’ils gagnent des étoiles.
Classé par santé, puis dynamique
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
High-performance, privacy-first on-device AI inference library for React Native, powered by PyTorch's ExecuTorch runtime
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)
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
A nearly-live implementation of OpenAI's Whisper.
Open-source State-of-the-art TTS model which runs on a CPU 😻
Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
On-device Speech AI for Apple Silicon
Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
SoTA open-source TTS
https://hf.co/hexgrad/Kokoro-82M
Instant voice cloning by MIT and MyShell. Audio foundation model.
A generative speech model for daily dialogue.
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
10 dépôts classés affichés sur 23. 12 jeunes projets sont présentés à part.
Moins de 12 mois, ou trop récents pour être évalués, et qui gagnent des étoiles.
The truly free, and open-source cross-platform CapCut replacement. Supports MCPs & API.
The open-source AI voice studio. Clone, dictate, create.
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
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 realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
AuK: An Open-Source Foundational Model for Speech Generation and Editing
A 100M-parameter multilingual TTS model for real-time CPU inference, voice cloning, and 48 kHz stereo generation
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).
