ChatTTS is a text-to-speech model designed specifically for dialogue scenarios such as LLM assistant.

• English
• Chinese
• Coming Soon...

You can refer to this video on Bilibili for the detailed description.

1. Conversational TTS: ChatTTS is optimized for dialogue-based tasks, enabling natural and expressive speech synthesis. It supports multiple speakers, facilitating interactive conversations.
2. Fine-grained Control: The model could predict and control fine-grained prosodic features, including laughter, pauses, and interjections.
3. Better Prosody: ChatTTS surpasses most of open-source TTS models in terms of prosody. We provide pretrained models to support further research and development.

• The main model is trained with Chinese and English audio data of 100,000+ hours.
• The open-source version on HuggingFace is a 40,000 hours pre-trained model without SFT.

• Open-source the 40k hour base model and spk_stats file
• Open-source VQ encoder and Lora training code
• Streaming audio generation without refining the text*
• Open-source the 40k hour version with multi-emotion control
• ChatTTS.cpp maybe? (PR or new repo are welcomed.)

It is intended for educational and research use, and should not be used for any commercial or legal purposes. The authors do not guarantee the accuracy, completeness, or reliability of the information. The information and data used in this repo, are for academic and research purposes only. The data obtained from publicly available sources, and the authors do not claim any ownership or copyright over the data.

ChatTTS is a powerful text-to-speech system. However, it is very important to utilize this technology responsibly and ethically. To limit the use of ChatTTS, we added a small amount of high-frequency noise during the training of the 40,000-hour model, and compressed the audio quality as much as possible using MP3 format, to prevent malicious actors from potentially using it for criminal purposes. At the same time, we have internally trained a detection model and plan to open-source it in the future.

GitHub issues/PRs are always welcomed.

For formal inquiries about the model and roadmap, please contact us at open-source@2noise.com.

• Group 1, 808364215 (Full)
• Group 2, 230696694 (Full)
• Group 3, 933639842

Will be uploaded to pypi soon according to 2noise#269

pip install git+https://github.com/2noise/ChatTTS

git clone https://github.com/2noise/ChatTTS
cd ChatTTS
conda create -n chattts
conda activate chattts
pip install -r requirements.txt

pip install --upgrade -r requirements.txt

python examples/web/webui.py

It will save audio to ./output_audio_xxx.wav

python examples/cmd/run.py "Please input your text."

import ChatTTS
from IPython.display import Audio
import torchaudio

chat = ChatTTS.Chat()
chat.load_models(compile=False) # Set to True for better performance

texts = ["PUT YOUR TEXT HERE",]

wavs = chat.infer(texts, )

torchaudio.save("output1.wav", torch.from_numpy(wavs[0]), 24000)

###################################
# Sample a speaker from Gaussian.

rand_spk = chat.sample_random_speaker()

params_infer_code = {
  'spk_emb': rand_spk, # add sampled speaker 
  'temperature': .3, # using custom temperature
  'top_P': 0.7, # top P decode
  'top_K': 20, # top K decode
}

###################################
# For sentence level manual control.

# use oral_(0-9), laugh_(0-2), break_(0-7) 
# to generate special token in text to synthesize.
params_refine_text = {
  'prompt': '[oral_2][laugh_0][break_6]'
} 

wavs = chat.infer(texts, params_refine_text=params_refine_text, params_infer_code=params_infer_code)

###################################
# For word level manual control.
text = 'What is [uv_break]your favorite english food?[laugh][lbreak]'
wavs = chat.infer(text, skip_refine_text=True, params_refine_text=params_refine_text,  params_infer_code=params_infer_code)
torchaudio.save("output2.wav", torch.from_numpy(wavs[0]), 24000)

inputs_en = """
chat T T S is a text to speech model designed for dialogue applications. 
[uv_break]it supports mixed language input [uv_break]and offers multi speaker 
capabilities with precise control over prosodic elements [laugh]like like 
[uv_break]laughter[laugh], [uv_break]pauses, [uv_break]and intonation. 
[uv_break]it delivers natural and expressive speech,[uv_break]so please
[uv_break] use the project responsibly at your own risk.[uv_break]
""".replace('\n', '') # English is still experimental.

params_refine_text = {
  'prompt': '[oral_2][laugh_0][break_4]'
} 
# audio_array_cn = chat.infer(inputs_cn, params_refine_text=params_refine_text)
audio_array_en = chat.infer(inputs_en, params_refine_text=params_refine_text)
torchaudio.save("output3.wav", torch.from_numpy(audio_array_en[0]), 24000)

For a 30-second audio clip, at least 4GB of GPU memory is required. For the 4090 GPU, it can generate audio corresponding to approximately 7 semantic tokens per second. The Real-Time Factor (RTF) is around 0.3.

This is a problem that typically occurs with autoregressive models (for bark and valle). It's generally difficult to avoid. One can try multiple samples to find a suitable result.

In the current released model, the only token-level control units are [laugh], [uv_break], and [lbreak]. In future versions, we may open-source models with additional emotional control capabilities.

• bark, XTTSv2 and valle demostrate a remarkable TTS result by an autoregressive-style system.
• fish-speech reveals capability of GVQ as audio tokenizer for LLM modeling.
• vocos which is used as a pretrained vocoder.

• wlu-audio lab for early algorithm experiments.

• Awesome-ChatTTS