#speech-synthesis Repositories
101 repositories total
Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoints (incl. OpenAI compatible), predefined voices, voice cloning, and large audiobook-scale text processing. Runs accelerated on NVIDIA (CUDA), AMD (ROCm), and CPU.
A multilingual model for long-form, multi-speaker dialogue synthesis with flexible speaker control and zero-shot voice cloning
๐ A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
StreamSpeech is an โAll in Oneโ seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.
Irina is a Russian voice assistant for offline work. Supports skills via plugins.
The core of VOICEVOX, a free-to-use, medium-quality text-to-speech software
AI-powered multi-voice audiobook generator โ LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
Make Azure natural TTS voices accessible to any SAPI 5-compatible application.
A talking LLM that runs on your own computer without needing the internet.
One-click production of viral videos: 1. Automatically extract benchmark copy 2. Automatically imitate copy 3. Automatically clone voice based on copy 4. Automatically generate AI anchor narration 5. Automatically add subtitles 6. Automatically add background music 7. Automatically add video titles 8. Automatically generate video covers 9. Automatically publish videos to various platforms
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
sanoTTS (เคธเคพเคจเฅ = โsmallโ in Nepali): a 294kโ2.27M-parameter neural TTS system that runs on a $3 chip, in the browser, or in Python, with low-latency streaming.
A Python wrapper for the high-quality vocoder "World"
Vui Nano โ a small, context-aware text-to-speech model trained on real conversations. 219M active parameters (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Includes a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.
The intention of this project is to unify the way various speech synthesis engines are used, support multiple speech synthesis engine adapters, and allow direct use as a module or startup of a backend service.
Thorsten-Voice: A free to use, offline working, high quality german TTS voice should be available for every project without any license struggling.
Unified automatic quality assessment for speech, music, and sound.
INTERSPEECH 2023-2024 Papers: A complete collection of influential and exciting research papers from the INTERSPEECH 2023-24 conference. Explore the latest advances in speech and language processing. Code included. Star the repository to support the advancement of speech technology!
Automatically Update Text-to-speech (TTS) Papers Daily using Github Actions (Update Every 12th hours)
Machine learning based speech synthesis Electron app, with voices from specific characters from video games
Hojo-TTS-Light is a lightweight speech generation model series developed by HojoAI, currently comprising 0.04B and 0.08B models.
High-quality and streaming Speech-to-Speech interactive agent in a single file. Streaming full-duplex voice interaction prototype intelligent agent implemented with only one file!
Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice
SummerTTS is a C++-based, standalone Chinese and English Text-to-Speech (TTS) project. It runs locally without the need for a network connection or external dependencies, allowing users to perform Chinese and English speech synthesis simply by completing a one-click build.
Keep track of big models in audio domain, including speech, singing, music etc.
StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
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.
VibeVoiceFusion is a full-stack, multi-speaker voice generation web system featuring LoRA fine-tuning, batch generation, and VRAM optimization. Based on Microsoft's VibeVoice (AR + diffusion architecture)