AI Audio

F5-TTS

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

Written mainly in Python. Released under the MIT licence.

OpenVoice

Instant voice cloning by MIT and MyShell. Audio foundation model.

Written mainly in Python. Released under the MIT licence.

Retrieval-based-Voice-Conversion-WebUI

Easily train a good VC model with voice data <= 10 mins!

Written mainly in Python. Released under the MIT licence.

TTS

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

Written mainly in Python. Released under the MPL-2.0 licence.

bark

🔊 Text-Prompted Generative Audio Model

Written mainly in Jupyter Notebook. Released under the MIT licence.

dia

A TTS model capable of generating ultra-realistic dialogue in one pass.

Written mainly in Python. Released under the Apache-2.0 licence.

faster-whisper

Faster Whisper transcription with CTranslate2

Written mainly in Python. Released under the MIT licence.

fish-speech

SOTA Open Source TTS

Written mainly in Python.

kokoro

https://hf.co/hexgrad/Kokoro-82M

Written mainly in JavaScript. Released under the Apache-2.0 licence.

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

Written mainly in Python. Released under the MIT licence.

whisper.cpp

Port of OpenAI's Whisper model in C/C++

Written mainly in C++. Released under the MIT licence.

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Written mainly in Python. Released under the BSD-2-Clause licence.