speech

MARS5 speech model (TTS) from CAMB.AI

💬 SpeechGPT is a web application that enables you to converse with ChatGPT.

Python library and CLI tool to interface with Google Translate's text-to-speech API

Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

Controllable and fast Text-to-Speech for over 7000 languages!

Free, easy, portable audio engine for games

Free, high-quality text-to-speech API endpoint to replace OpenAI, Azure, or ElevenLabs

Praat: Doing Phonetics By Computer

Open-Source Large Vocabulary Continuous Speech Recognition Engine

Community list of startups working with AI in audio and music technology

SALMONN family: A suite of advanced multi-modal LLMs

General Speech Restoration

Controllable Transcription. Verbatim ( every, filler, pause, stutter, vocal sound) , or intended ( what the speaker meant to say, optimized for readability) with word-level timestamps.

自然语言处理领域下的相关论文（附阅读笔记），复现模型以及数据处理等（代码含TensorFlow和PyTorch两版本）

MTools 是一个功能强大的多功能桌面应用程序，集成了音视频处理、图片编辑、文本操作和编码工具，内置AI增强功能。旨在简化您的工作流程，提升生产效率

StreamSpeech is an “All in One” seamless model for offline and simultaneous speech recognition, speech translation and speech synthesis.

Videos, notes and experiments to understand deep learning

Tools for handling multimodal data in machine learning projects.

[Unofficial] PyTorch implementation of "Conformer: Convolution-augmented Transformer for Speech Recognition" (INTERSPEECH 2020)

A Python wrapper for Kaldi

An Open-Sourced LLM-empowered Foundation TTS System

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.

A unified multimodal language model based on discrete sequence modeling

基于PaddlePaddle实现端到端中文语音识别，从入门到实战，超简单的入门案例，超实用的企业项目。支持当前最流行的DeepSpeech2、Conformer、Squeezeformer模型

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 real-time interactive Omni Avatar built on LiveKit, which allows you to seamlessly integrate with any open source Avatar components (real-time model, visual, voice, memory, search, etc.).

🎧 🎼 The MOST ADVANCED JavaFX Media Player

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

Allosaurus is a pretrained universal phone recognizer for more than 2000 languages