speech-synthesis

Tensorflow Implementation of Expressive Tacotron

An overview of the AI-as-a-service landscape

🐍 🤖 Pip installable package for StyleTTS 2 human-level text-to-speech and voice cloning

Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)

Spokestack is a library that allows a user to easily incorporate a voice interface into any Python application with a focus on embedded systems.

Google's SoundStorm: Efficient Parallel Audio Generation

Easy fine-tuning for Qwen3-TTS: Fast voice cloning and high-quality multilingual speech synthesis.

Fine-tuning toolkit for Chatterbox TTS & Chatterbox TURBO models. Supports 23 languages with smart vocabulary extension. Features offline preprocessing, automatic VAD trimming, and voice cloning capabilities. Train custom TTS models with your own dataset in LJSpeech and file-based format.

A multilingual ASR model that can recognize ten Turkic languages—Azerbaijani, Bashkir, Chuvash, Kazakh, Kyrgyz, Sakha, Tatar, Turkish, Uyghur, and Uzbek.

NOVA is a customizable voice assistant made with Node.js.

A speech-to-text framework and bot for Discord. Take control of your Discord server using speech and voice commands. Can also be useful for hearing impaired and deaf people.

Add Hume AI to any TypeScript project

Polyfill Web Speech API with Cognitive Services for both speech-to-text and text-to-speech service.

Unofficial Go client for the ElevenLabs API: text-to-speech, speech-to-text, sound generation, and voice management.

🎤 🔉 Projeto de um SPA desenvolvido com Quasar Framework 1.0 + Speech API para capturar áudio e transformar em texto, ou utilizar um texto como base para a aplicação emitir um áudio.

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Spokestack: give your React Native app a voice interface!

the first industrial-scale open-source Kazakh speech corpus. KSC2 corpus subsumes the previously introduced two corpora: KSC and KazakhTTS2 and supplements additional data from other sources. KSC2 contains around 1.2k hours of high-quality transcribed data comprising over 600k utterances.

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cloning, and 23 languages.

End-to-end Solution for Speech Recognition, Text Translation, and Text-to-Speech for iOS using Amazon Translate and Amazon Polly as AWS Machine Learning managed services.