Speech Libraries - Page 1

Clone a voice in 5 seconds to generate arbitrary speech in real-time

Python 42399Updated: 2 y ago License: Proprietary (Proprietary)

Robust Speech Recognition via Large-Scale Weak Supervision

Python 39256Updated: 2 y ago License: Permissive (MIT)

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

C++ 22108Updated: 2 y ago License: Weak Copyleft (MPL-2.0)

SoftVC VITS Singing Voice Conversion

Python 15411Updated: 2 y ago License: Strong Copyleft (AGPL-3.0)

🧠 Leon is your open-source personal assistant.

TypeScript 12924Updated: 2 y ago License: Permissive (MIT)

kaldi-asr/kaldi is the official location of the Kaldi project.

Shell 12835Updated: 2 y ago License: Proprietary (Proprietary)

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Python 12468Updated: 2 y ago License: Weak Copyleft (MPL-2.0)

Offline documentation browser inspired by Dash

C++ 10486Updated: 2 y ago License: Strong Copyleft (GPL-3.0)

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Python 8722Updated: 2 y ago License: Proprietary (Proprietary)

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Python 7725Updated: 2 y ago License: Permissive (Apache-2.0)

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

Jupyter Notebook 7519Updated: 2 y ago License: Weak Copyleft (MPL-2.0)

A multi-voice TTS system trained with an emphasis on quality

Python 7408Updated: 2 y ago License: Permissive (Apache-2.0)

Manipulate audio with a simple and easy high level interface

Python 7332Updated: 2 y ago License: Permissive (MIT)

Speech recognition module for Python, supporting several engines and APIs, online and offline.

Python 7239Updated: 2 y ago License: Permissive (BSD-3-Clause)

NeMo: a toolkit for conversational AI

Python 7027Updated: 2 y ago License: Permissive (Apache-2.0)

End-to-End Speech Processing Toolkit

Python 6684Updated: 2 y ago License: Permissive (Apache-2.0)

:speech_balloon: Speech recognition for your site

JavaScript 6366Updated: 2 y ago License: Permissive (MIT)

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

Python 6327Updated: 2 y ago License: Permissive (MIT)

Facebook AI Research's Automatic Speech Recognition Toolkit

C++ 6241Updated: 2 y ago License: Proprietary (Proprietary)

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Jupyter Notebook 5750Updated: 2 y ago License: Permissive (Apache-2.0)

Facebook AI Research's Automatic Speech Recognition Toolkit

Python 5531Updated: 4 y ago License: Proprietary (Proprietary)

Voice data <= 10 mins can also be used to train a good VC model!

Python 4863Updated: 2 y ago License: Permissive (MIT)

Speech and Vision Based Intelligent Personal Assistant

Java 4839Updated: 4 y ago License: Proprietary (Proprietary)

🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目，支持ChatGPT多轮对话能力，还可能是首个支持脑机交互的开源智能音箱项目。

Python 4664Updated: 2 y ago License: Permissive (MIT)

Tacotron 2 - PyTorch implementation with faster-than-realtime inference

Jupyter Notebook 4497Updated: 2 y ago License: Permissive (BSD-3-Clause)

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Python 4351Updated: 2 y ago License: Permissive (MIT)

Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox. It also generates a suggested response using OpenAI's GPT-3.5 for the user to say based on the live transcription of the conversation.

Python 4253Updated: 2 y ago License: Permissive (MIT)

Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow

Python 3746Updated: 2 y ago License: Permissive (Apache-2.0)

Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple

Jupyter Notebook 3739Updated: 2 y ago License: Proprietary (Proprietary)

A small speech recognizer

C 3387Updated: 2 y ago License: Proprietary (Proprietary)

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art Speech Synthesis for Tensorflow 2 (supported including English, French, Korean, Chinese, German and Easy to adapt for other languages)

Python 3375Updated: 2 y ago License: Permissive (Apache-2.0)

Common Voice is part of Mozilla's initiative to help teach machines how real people speak.

TypeScript 3156Updated: 2 y ago License: Weak Copyleft (MPL-2.0)

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Jupyter Notebook 3116Updated: 2 y ago License: Permissive (MIT)

Production First and Production Ready End-to-End Speech Recognition Toolkit

C++ 3072Updated: 2 y ago License: Permissive (Apache-2.0)

On-device wake word detection powered by deep learning

Python 3030Updated: 2 y ago License: Permissive (Apache-2.0)

Enhancements tracking repo for Kubernetes

Go 2907Updated: 2 y ago License: Permissive (Apache-2.0)

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)

Python 2787Updated: 2 y ago License: Permissive (MIT)

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

Python 2729Updated: 4 y ago License: Permissive (MIT)

Lingvo

Python 2727Updated: 2 y ago License: Permissive (Apache-2.0)

A speech recognition library for the web

JavaScript 2578Updated: 2 y ago License: Proprietary (Proprietary)

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

TypeScript 2508Updated: 2 y ago License: Permissive (MIT)

A python package to analyze and compare voices with deep learning

Python 2291Updated: 2 y ago License: Permissive (Apache-2.0)

WaveNet vocoder

Python 2170Updated: 2 y ago License: Proprietary (Proprietary)

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

Python 2169Updated: 2 y ago License: Strong Copyleft (AGPL-3.0)

DeepMind's Tacotron-2 Tensorflow implementation

Python 2166Updated: 2 y ago License: Permissive (MIT)

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

Python 2142Updated: 2 y ago License: Proprietary (Proprietary)

eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.

C 2099Updated: 2 y ago License: Strong Copyleft (GPL-3.0)

Spot SDK repo

Python 2077Updated: 2 y ago License: Proprietary (Proprietary)

Offline private voice assistant for many human languages

Shell 2000Updated: 2 y ago License: Permissive (MIT)

MARY TTS -- an open-source, multilingual text-to-speech synthesis system written in pure java

Java 1992Updated: 2 y ago License: Proprietary (Proprietary)