Speech Libraries - Page 3

Simple, hackable offline speech to text - using the VOSK-API.

Python 956Updated: 1 y ago License: Strong Copyleft (GPL-3.0)

Subtitle Speech Synchronizer

C++ 943Updated: 1 y ago License: Strong Copyleft (GPL-3.0)

Botium Speech Processing

JavaScript 939Updated: 1 y ago License: Permissive (MIT)

A Python wrapper for Kaldi

Python 936Updated: 2 y ago License: Permissive (Apache-2.0)

Unofficial PyTorch implementation of Google AI's VoiceFilter system

Python 912Updated: 2 y ago License: No License (No License)

Creates audio supercuts.

Python 912Updated: 3 y ago License: Permissive (MIT)

Chinese real time voice cloning (VC) and Chinese text to speech (TTS). 好用的中文语音克隆兼中文语音合成系统，包含语音编码器、语音合成器、声码器和可视化模块。

Python 890Updated: 3 y ago License: No License (No License)

Espresso: A Fast End-to-End Neural Speech Recognition Toolkit

Python 887Updated: 3 y ago License: Proprietary (Proprietary)

an open-source implementation of sequence-to-sequence based speech processing engine

C++ 869Updated: 2 y ago License: Permissive (Apache-2.0)

Audio MODEM Communication Library in Python

Python 864Updated: 2 y ago License: Proprietary (Proprietary)

:speech_balloon: SpeechPy - A Library for Speech Processing and Recognition: http://speechpy.readthedocs.io/en/latest/

Python 839Updated: 3 y ago License: Permissive (Apache-2.0)

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

Jupyter Notebook 839Updated: 1 y ago License: Permissive (Apache-2.0)

Audio Waveform Data Manipulation API – resample, offset and segment waveform data in JavaScript.

JavaScript 824Updated: 3 y ago License: Weak Copyleft (LGPL-3.0)

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer

Jupyter Notebook 817Updated: 2 y ago License: Permissive (Apache-2.0)

The official repository of the Eesen project

C++ 816Updated: 2 y ago License: Permissive (Apache-2.0)

A fast, local neural text to speech system

C++ 794Updated: 1 y ago License: Permissive (MIT)

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.

Python 788Updated: 2 y ago License: Permissive (MIT)

The Implementation of FastSpeech based on pytorch.

Python 785Updated: 1 y ago License: Permissive (MIT)

Closed Captioning OBS plugin using Google Speech Recognition

C++ 785Updated: 1 y ago License: Strong Copyleft (GPL-2.0)

Jarvis.sh is a simple configurable multi-lang assistant.

Shell 780Updated: 2 y ago License: Permissive (MIT)

Mellotron: a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data

Jupyter Notebook 773Updated: 2 y ago License: Permissive (BSD-3-Clause)

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

Python 766Updated: 1 y ago License: Permissive (MIT)

End to end text to speech system using gruut and onnx

Python 766Updated: 2 y ago License: Permissive (MIT)

A chat app that transcribes audio in real-time, streams back a response from a language model, and synthesizes this response as natural-sounding speech.

JavaScript 730Updated: 1 y ago License: Permissive (MIT)

OpenAI Whisper ASR Webservice API

Python 728Updated: 1 y ago License: Permissive (MIT)

Open STT

Python 727Updated: 1 y ago License: Proprietary (Proprietary)

Chinese text-to-speech engine

C++ 719Updated: 3 y ago License: Proprietary (Proprietary)

中文语音识别

Python 716Updated: 2 y ago License: No License (No License)

A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.

Python 709Updated: 2 y ago License: No License (No License)

Adapt Intent Parser

Python 704Updated: 3 y ago License: Permissive (Apache-2.0)

Audio landmark fingerprinting as a Node Stream module

JavaScript 704Updated: 3 y ago License: Weak Copyleft (MPL-2.0)

A lightweight, simple-to-use, RNN wake word listener

Python 700Updated: 1 y ago License: Permissive (Apache-2.0)

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

Python 687Updated: 4 y ago License: Permissive (Apache-2.0)

Tools for handling speech data in machine learning projects.

Python 686Updated: 1 y ago License: Permissive (Apache-2.0)

Node.js client for Google Cloud Speech: Speech to text conversion powered by machine learning.

TypeScript 683Updated: 2 y ago License: Permissive (Apache-2.0)

A fast local neural text to speech engine for Mycroft

Python 676Updated: 2 y ago License: Strong Copyleft (AGPL-3.0)

text to speech toolkit. 好用的中文语音合成工具箱，包含语音编码器、语音合成器、声码器和可视化模块。

Python 661Updated: 2 y ago License: Permissive (MIT)

Python AI assistant 🧠

Python 660Updated: 2 y ago License: Permissive (MIT)

Example scripts for voice assistants created with the Alan AI Platform.

JavaScript 659Updated: 1 y ago License: No License (No License)

A PyTorch Implementation of End-to-End Models for Speech-to-Text

Python 654Updated: 2 y ago License: Permissive (Apache-2.0)

A Speaker Recognition System

C++ 645Updated: 3 y ago License: Permissive (Apache-2.0)

:speech_balloon: An On-Premises, Streaming Speech Recognition System

Python 642Updated: 3 y ago License: Permissive (MIT)

Microsoft Text-to-Speech API sample code in several languages, part of Cognitive Services.

C# 635Updated: 1 y ago License: Proprietary (Proprietary)

An open "intelligent" assistant for the web that can listen to you and learn.

JavaScript 628Updated: 4 y ago License: Proprietary (Proprietary)

An audio/acoustic activity detection and audio segmentation tool

Python 626Updated: 2 y ago License: Permissive (MIT)

语音api示例

Java 623Updated: 1 y ago License: No License (No License)

JavaScript implementation of Japanese morphological analyzer

JavaScript 620Updated: 3 y ago License: Permissive (Apache-2.0)

Thousands of everyday sounds, organized using machine learning.

JavaScript 615Updated: 3 y ago License: Permissive (Apache-2.0)

Mycroft's TTS engine, based on CMU's Flite (Festival Lite)

C 615Updated: 3 y ago License: Proprietary (Proprietary)

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"

Python 613Updated: 1 y ago License: Permissive (MIT)