Audio computing

VALL-E is a neural codec language model using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather. VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as a prompt. We also extend VALL-E and train a multi-lingual conditional codec language model. VALL-E X can generate high-quality speech in the target language via just one speech utterance in the source language as a prompt while preserving the unseen speaker’s voice, emotion, and acoustic environment.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Inference and training library for high-quality TTS models. - huggingface/parler-tts

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

Voicery creates natural-sounding Text-to-Speech (TTS) engines and custom brand voices for enterprise. Our solutions leverage cutting-edge deep-learning research optimized for your business use-case and technical infrastructure.

Brand new TTS solution. Contribute to fishaudio/fish-speech development by creating an account on GitHub.

Audio translated automatically using AI voice cloning technology.

GNOME audio player for transcription

bigWav: free and private audio transcription and annotation

Award-winning AI Voice Generator and text to speech software with 500+ voices in 100 languages. Realistic AI Voices with Online Video Editor. Clone your own voice.

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation. - mkiol/dsnote

Explore Speech to Note for top-notch voice to text, note speech, and speak writer solutions. Our AI technology powered by GPT-4o ensures easy conversion of your voice into written notes.

Pico TTS: text to speech voice sinthesizer from SVox, included in Android AOSP - ihuguet/picotts

Watson Speech to Text is an API that transcribes speech to text in a variety of languages. It’s available as SaaS or for self-hosting.

Turn text into natural-sounding speech in 220+ voices across 40+ languages and variants with an API powered by Google’s machine learning technology.

Das Thorsten-Voice Projekt stellt kostenlos deutsche, AI/KI erzeugte Text to Speech (TTS) Stimmen bereit die ohne Internet funktionieren.

Thorsten-Voice: A free to use, offline working, high quality german TTS voice should be available for every project without any license struggling. - thorstenMueller/Thorsten-Voice

Home page of OVOS

NVDA, the free and open source Screen Reader for Microsoft Windows - nvaccess/nvda

Make Linux speak what's on the screen: clearly and securely. - evuraan/mintPiper

This project is aimed at developing and maintaining the NVDA IBMTTS driver. IBMTTS is a synthesizer similar to Eloquence. Please send your ideas and contributions here! - davidacm/NVDA-IBMTTS-Driver

This add-on implements a speech synthesizer driver for NVDA using neural TTS models. It supports Piper - mush42/sonata-nvda

Contribute to CrashXBETAX/Text_To_Speech_Live_WinUI3_Public development by creating an account on GitHub.

a free and open source speech synthesizer for Russian and other languages - RHVoice/RHVoice

A text to speech GTK+ front-end for eSpeak and mbrola to play a text in many languages with settings for voice, pitch, volume and speed - muflone/gespeaker

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

Common high-level interface to speech synthesis. Contribute to brailcom/speechd development by creating an account on GitHub.