Trending Voice AI Tools

A unified multi-language G2P (Grapheme-to-Phoneme) library for Kokoro TTS.

A Python library for Kokoro TTS (Text-to-Speech) using ONNX runtime.

Google Text to Speech for Node.js — modern, typed, zero deprecated dependencies.

Helper package for using quantized versions of the Indic ASR Model by AI4Bharat.

OpenAI-compatible ASR server with pluggable local backends (Parakeet,...

React Native Turbo Module to access Speech Recognition in Android & iOS

Speech Engine is a Python package that provides a simple interface for...

Easily fix common corrections in speech!

Open-source Python SDK for real-time Voice AI, voice agents, streaming...

espeakNG plugin

Library for working with a range of technologies for speech recognition and...

Lightweight offline voice assistant for hands-free music control (YouTube...

A streamlined, Kokoro-based text-to-speech library with streaming support.

Utils to modify pronunciation dictionaries.

Integrate Typecast AI TTS into your n8n workflows with this community node.

Microsoft Edge text-to-speech for Expo and React Native

Automatically generate voice narration for your Mintlify documentation.

API wrapper for the Dectalk TTS system

Convert EPUB files to audiobooks using Kokoro ONNX TTS

An innovative, open-source voice assistant powered by OpenAI's GPT-3,...

阿里云智能语音处理 Node 模块。

Ease of use for Speech to Text

Power-tool wrapper around the browser Web Speech API —

Generate speech audio from super long text through machine.

Repositório do módulo de geração de texto para fala Google, gTTS.

Library to generate TTS directly from Talkify.net APIs

Simple TTS (Text-To-Speech) broker for Python

Syntactic sugar sprinkled on top of MoviePy and AI components to allow...

🔊 Download pronunciation audio files from Google's dictionary service....

Get spoken alerts when Claude Code needs permission or finishes a task — so...

Node.js module that provides bindings for the DecTalk Text-To-Speech library

Slightly more consistent Text-to-speech for Web and a wrapper around speechSynthesis

Offline, cross-platform Python text-to-speech and sound notifications....

Open protocol & middleware for Indian language voice agents — STT→LLM→TTS in...

Kaia.ai platform's JS client library

Handsfree for Web module useful to ask for start or stop listening for voice commands

[Maintainer Required] A light-weight python library REST agent for Dialogflow

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

A modular framework for building VoIP-Agent applications.

A simple text-to-speech library using system native tts engines for Node.js

galician tts plugin for OVOS

🔈 A custom html element makes Text-To-Speech function easier to use on your...

A browser extension for Google Chrome. Provides reader view, saving articles...

vocal-stack is a high-performance utility library for developers building...

A simple, high-quality voice conversion tool focused on ease of use and performance.

💬 A JS/TS framework for opening the possibilities for what you can do with text.

edge-tts in Bun.

Enhance AWS Polly TTS pronunciation for english words within russian text

Using AWS Polly requires SSML files for a better optimised text to speech...

a cross-platform tts(text to speak) player

On-device wake word detection powered by deep learning

A Promise tts api, it depend on browser api window.speechSynthesis

Generate AWS Polly speech output data from SSML files!

rtts is an open source JavaScript package for text to speech conversion

A lightweight Python package for Automatic Speech Recognition using ONNX models

Package that allows the user to talk/text to a customizable avatar. Uses...

A unified TypeScript interface for browser speech synthesis and Eleven Labs...

A source of python package which converts language styles in speech to its...

A robust WebVTT to SRT converter optimized for AI transcriptions (Whisper,...

Give your AI agents a voice — TTS, phone calls, SMS, email, webhooks. One...

NectarSTT (Nectar Speech To Text) is a Python-based speech recognition...

return MP3 audio as a stream from given text

RxJS wrapper for speech recognition Web API

A python package for whisper normalizer

Streaming speech recognition running natively and in the browser. A pure...

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

End-to-end realtime stack for connecting humans and AI

🌈一个跨平台的划词翻译和OCR软件 | A cross-platform software for text translation and recognition.

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

A fast, local neural text to speech system

Video translation and dubbing tool powered by LLMs. The video translator...

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation....

A sound cloning tool with a web interface, using your voice or any sound to...

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

一个简单的本地网页界面，使用ChatTTS将文字合成为语音，同时支持对外提供API接口。A simple native web interface...

High-quality multi-lingual text-to-speech library by MyShell.ai. Support...

Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS,...

🎤 微软语音合成工具，使用 Electron + Vue + ElementPlus + Vite 构建。

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper

:stuck_out_tongue_closed_eyes: TensorFlowTTS: Real-Time State-of-the-art...

An unofficial PyTorch implementation of the audio LM VALL-E

Whisper & Faster-Whisper standalone executables for those who don't want to...

MARS5 speech model (TTS) from CAMB.AI

aeneas is a Python/C library and a set of tools to automagically synchronize...

Offline private voice assistant for many human languages

🚀 一键部署（含离线整合包）！基于 ChatTTS ，支持流式输出、音色抽卡、长音频生成和分角色朗读。简单易用，无需复杂安装。

This is a python API which allows you to get the transcript/subtitles for a...

Readest is a modern, feature-rich ebook reader designed for avid readers...

A nearly-live implementation of OpenAI's Whisper.

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

An Open Source text-to-speech system built by inverting Whisper.

这是一个Android系统TTS应用，内置微软演示接口，可自定义HTTP请求，可导入其他本地TTS引擎，以及根据中文双引号的简单旁白/对话识别朗读...

faster_whisper GUI with PySide6

MARY TTS -- an open-source, multilingual text-to-speech synthesis system...

Lingvo

openctp提供CTP股票期权、中泰证券XTP、华鑫证券奇点TORA、东方证券OST、东方财富证券EMT、盈透证券TWS、易盛TAP、量投QDP等各通道...

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

A small speech recognizer

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in...

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System