Repo AI đang lênCập nhật hằng ngày từ GitHub

Connectionist Temporal Classification (CTC) decoding algorithms: best path, beam search, lexicon search, prefix search, and token passing. Implemented in Python.

🔥🔥 Kokoro in Rust. https://huggingface.co/hexgrad/Kokoro-82M Insanely fast, realtime TTS with high quality you ever have.

The official repository of the Eesen project

Build real time speech2text web apps using OpenAI's Whisper https://openai.com/blog/whisper/

Golang implementation of Graphite/Carbon server with classic architecture: Agent -> Cache -> Persister

AI VTuber with LLM, ASR, TTS, OCR, CV and more technologies to live stream or play Minecraft with you.

Voxtral ASR & TTS running natively and in the browser. A Rust implementation of Mistral's Voxtral mini realtime ASR / TTS using the Burn ML framework

A 100% private AI voice transcription app that converts speech to text in 100+ languages. Built with Compose Multiplatform for Android & iOS using Whisper AI - no cloud uploads, all processing happens on-device for complete privacy. Reach out directly on: support@notelyvoice.ai

A modular Swift SDK for audio processing with MLX on Apple Silicon

Terminal eBook Reader with Audiobook-Quality Text-to-Speech — Supports EPUB, PDF, DOCX, HTML, RTF, TXT, and MD.

A fully local and private Speech-To-Text app, offering multiple model backends, diarization & calendar mode - Available for Windows, macOS & Linux

Speech to Text to Speech. Song now playing. Sends text as OSC messages to VRChat to display on avatar. (STTTS) (Speech to TTS) (VRC STT System) (VTuber TTS)

C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment, and more

🎤 Lobe TTS - A high-quality & reliable TTS/STT library for Server and Browser

React Native binding of whisper.cpp.

Generate transcripts for audio and video content with a user friendly UI, powered by Open AI's Whisper with automatic translations and download videos automatically with yt-dlp integration

a list of demo websites for automatic music generation research

Multi-source Translation

Stephanie is an open-source platform built specifically for voice-controlled applications as well as to automate daily tasks imitating much of an virtual assistant's work.

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit

Project that allows one to use a microphone with OpenAI whisper.

🎤 The easiest way to transcribe audio in Swift

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.

Deep learning for audio processing

A real-time silent speech recognition tool.

Your CrewAI Powered Video Editing Assistant

📦 快速转化「中文数字」和「阿拉伯数字」～ (最新特性：分数，日期、温度等转化）

Augmentative and Alternative Communication (AAC) system with text-to-speech for the browser

🔊 Kokoro Web: Free AI text-to-speech, online or self-hosted, OpenAI compatible!

Private and on-device speech recognition keyboard and service for Android.

Running speech to text model (whisper.cpp) in Unity3d on your local machine.

Flutter Text to Speech package

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

MimikaStudio - A local-first application for macOS (Apple Silicon) + Agentic MCP Support

Chinese text normalization for speech processing

Thorsten-Voice: A free to use, offline working, high quality german TTS voice should be available for every project without any license struggling.

A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.

TTSFM mirrors OpenAI's TTS service, providing a compatible interface for text-to-speech conversion with multiple voice options for free.

🐸 collection of TTS papers

Easily create Piper text-to-speech models in any voice. Make a text-to-speech model with your own voice recordings, or use thousands of RVC voices. Works offline on a Raspberry pi. Rapidly record custom datasets for any metadata.csv file and listen to your model as it is training.

Speech to Text and KB input captions for OBS, VRChat, Twitch chat and Discord

Adapt Intent Parser

Open Source, Privacy-First, macOS-Native AI Meeting Summary

On-device Speech-to-Intent engine powered by deep learning

A Generative Flow for Text-to-Speech via Monotonic Alignment Search

Open-Source Toolkit for End-to-End Speech Recognition leveraging PyTorch-Lightning and Hydra.

Fully automated video maker using motion graphics and text-to-speech synthesis to turn newsletters into daily YouTube videos.

The code for the bark-voicecloning model. Training and inference.

语音api示例