Text to Speech

[admin]

TTS

1. Kokoro

Kokoro TTS: Advanced AI Text-to-Speech Model with 82M parameters

Kokoro TTS - a Hugging Face Space by hexgrad

2. Zonos

Zyphra

Zyphra/Zonos-v0.1-hybrid · Hugging Face

Supports mandarin (cmn) and cantonese (yue)

Zyphra/Zonos-v0.1-hybrid · Language code mapping request

3. Reviews

Increasing number of high quality neural network based TTS are now available:

source: AIPrintify

Notes:

• Spark-TTS license changed to non-commercial

Language Code

A lot of TTS use the language code based on espeak-ng:

• espeak-ng/docs/languages.md at master · espeak-ng/espeak-ng · GitHub

Cantonese

• Zonos
  chinese language code · Issue #26 · Zyphra/Zonos · GitHub
• Cosyvoice2-0.5B
  CosyVoice2-0.5B | AI Model Details
• E2-F5 TTS
  Cantonese needed! · Issue #37 · SWivid/F5-TTS · GitHub
• GPT-SoVITS
  GitHub - RVC-Boss/GPT-SoVITS: 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

[admin]

Alternatives

You can pick from MANY open sourced Text to Speech Engines

1. GitHub - suno-ai/bark: 🔊 Text-Prompted Generative Audio Model
2. GitHub - metavoiceio/metavoice-src: Foundational model for human-like, expressive TTS
3. GitHub - coqui-ai/TTS: 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
4. https://github.com/myshell-ai/MeloTTS
5. GitHub - jishengpeng/ControlSpeech: [ACL 2025 Main] ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control With Decoupled Codec
6. GitHub - fishaudio/fish-speech: SOTA Open Source TTS
7. GitHub - jaywalnut310/vits: VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
8. GitHub - 2noise/ChatTTS: A generative speech model for daily dialogue.
9. GitHub - huggingface/parler-tts: Inference and training library for high-quality TTS models.
10. GitHub - yl4579/StyleTTS2: StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
11. https://github.com/jasonppy/VoiceCraft
12. GitHub - neonbjb/tortoise-tts: A multi-voice TTS system trained with an emphasis on quality
13. balacoon/tts · Hugging Face
14. GitHub - snakers4/silero-models: Silero Models: pre-trained text-to-speech models made embarrassingly simple
15. https://community.openconversational.ai/
16. https://marytts.github.io/
17. GitHub - ihuguet/picotts: Pico TTS: text to speech voice sinthesizer from SVox, included in Android AOSP

[admin]

VITS

The default TTS engine Piper is based on VITS:

VITS - TTS 0.22.0 documentation

https://medium.com/@vansh_/using-vits-for-text-to-speech-tts-with-code-6e4e2c25e57d

Cantonese

GitHub - Keith-Hon/vits-cantonese: Cantonese Text to Speech with VITS implementation

[admin]

StyleTTS2

• GitHub - yl4579/StyleTTS2: StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

Demo

• Audio Samples from "Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech"

Server

• GitHub - lxe/tts-server: A simple TTS server for generating speech using StyleTTS2

[admin]

Piper

• GitHub - rhasspy/piper: A fast, local neural text to speech system

• Piper-Training-Guide-with-Screen-Reader/README.md at main · ZachB100/Piper-Training-Guide-with-Screen-Reader · GitHub

Under Windows - Team AI in Windows