license: cc-by-sa-4.0
OuteTTS Version 0.3
OuteTTS version 0.3 introduces multiple model variants tailored for diverse use cases.
This release significantly enhances the naturalness and coherence of speech synthesis by adding punctuation support, improving the flow and clarity of generated speech.
The following punctuation marks are supported: '.', '!', '?', ',', '"', '„', '¡', '¿', '…', '...', '。', '！', '？', '，', '؟'. These are converted into special tokens, for instance, . is transformed into <|period|>.
Additionally, the models were trained on refined and extended datasets, offering broader linguistic coverage. With this version, two new languages, German (de) and French (fr), are supported, bringing the total to six languages: English (en), Japanese (jp), Korean (ko), Chinese (zh), French (fr), and German (de).
Experimental voice control features are also included, though they are in very early stage of development. Due to limited data, these features may produce inconsistent results and might sometimes be ignored by the model.
Special thanks to Hugging Face 🤗 for providing the GPU grant that made training this model possible!
Available Variants
OuteTTS-0.3-500M
- Base: Qwen2.5-0.5B (Apache-2.0)
- License: CC-BY-SA-4.0
- Training: 10,000 hours of speech audio (~4 billion tokens)
- Supported Languages: en, jp, ko (small dataset), zh, fr, de
OuteTTS-0.3-1B
- Base: OLMO-1B (Apache-2.0)
- License: CC-BY-NC-SA-4.0 (Incorporates the Emilia dataset, for improved quality)
- Training: 20,000 hours of speech audio (~8 billion tokens)
- Supported Languages: en, jp, ko, zh, fr, de
Showcase Video
Installation
Install the OuteTTS package via pip:
pip install outetts --upgrade
Usage
Quick Start: Full Basic Example
import outetts
# Configure the model
model_config = outetts.HFModelConfig_v2(model_path="OuteAI/OuteTTS-0.3-1B")
# Initialize the interface
interface = outetts.InterfaceHF(model_version="0.3", cfg=model_config)
# You can create a speaker profile for voice cloning, which is compatible across all backends.
# speaker = interface.create_speaker(
# audio_path="path/to/audio/file.wav",
# transcript=None, # Set to None to use Whisper for transcription
# whisper_model="turbo", # Optional: specify Whisper model (default: "turbo")
# whisper_device=None, # Optional: specify device for Whisper (default: None)
# )
# interface.save_speaker(speaker, "speaker.json")
# speaker = interface.load_speaker("speaker.json")
# Print available default speakers
interface.print_default_speakers()
# Load a default speaker
speaker = interface.load_default_speaker(name="en_male_1")
# Generate speech
output = interface.generate(
text="Speech synthesis is the artificial production of human speech.",
temperature=0.1,
repetition_penalty=1.1,
max_length=4096,
speaker=speaker
)
# Save the generated speech to a file
output.save("output.wav")
For additional usage examples and recommendations, visit the GitHub repository.
Dataset Attribution
The OuteTTS-0.3-500M training data incorporates various publicly available speech datasets. Below is a summary of the key data sources:
- Mozilla Common Voice: CC-0
- MLCommons People's Speech Dataset (selected portions): CC-BY 4.0
- Noisy Speech Database (Edinburgh DataShare): CC BY 4.0
- Multilingual LibriSpeech (MLS): CC BY 4.0
- CSTR VCTK Corpus (Edinburgh DataShare): CC BY 4.0
- THCHS-30 (Open Speech and Language Resources): Apache-2.0
- Zeroth-Korean (Open Speech and Language Resources): CC BY 4.0
- Aishell (Open Speech and Language Resources): Apache-2.0
- Other permissively licensed datasets
Credits & References
Special acknowledgment to the open-source community and researchers for their valuable contributions.