outetts 0.4.4

OuteTTS

🌐 Website | 🤗 Hugging Face | 💬 Discord | 𝕏 X (Twitter) | 📰 Blog

Compatibility

OuteTTS supports the following backends:

⚡ Batched RTF Benchmarks

Tested with NVIDIA L40S GPU

Installation

OuteTTS Installation Guide

OuteTTS now installs the llama.cpp Python bindings by default. Therefore, you must specify the installation based on your hardware. For more detailed instructions on building llama.cpp, refer to the following resources: llama.cpp Build and llama.cpp Python

Pip:

pip install outetts --upgrade

CMAKE_ARGS="-DGGML_CUDA=on" pip install outetts --upgrade

CMAKE_ARGS="-DGGML_HIPBLAS=on" pip install outetts --upgrade

CMAKE_ARGS="-DGGML_VULKAN=on" pip install outetts --upgrade

CMAKE_ARGS="-DGGML_METAL=on" pip install outetts --upgrade

Usage

📚 Documentation

For a complete usage guide, refer to the interface documentation here:

Basic Usage

import outetts

# Initialize the interface
interface = outetts.Interface(
    config=outetts.ModelConfig.auto_config(
        model=outetts.Models.VERSION_1_0_SIZE_1B,
        # For llama.cpp backend
        backend=outetts.Backend.LLAMACPP,
        quantization=outetts.LlamaCppQuantization.FP16
        # For transformers backend
        # backend=outetts.Backend.HF,
    )
)

# Load the default speaker profile
speaker = interface.load_default_speaker("EN-FEMALE-1-NEUTRAL")

# Or create your own speaker profiles in seconds and reuse them instantly
# speaker = interface.create_speaker("path/to/audio.wav")
# interface.save_speaker(speaker, "speaker.json")
# speaker = interface.load_speaker("speaker.json")

# Generate speech
output = interface.generate(
    config=outetts.GenerationConfig(
        text="Hello, how are you doing?",
        speaker=speaker,
    )
)

# Save to file
output.save("output.wav")

Usage Recommendations for OuteTTS version 1.0

Speaker Reference

The model is designed to be used with a speaker reference. Without one, it generates random vocal characteristics, often leading to lower-quality outputs. The model inherits the referenced speaker's emotion, style, and accent. Therefore, when transcribing to other languages with the same speaker, you may observe the model retaining the original accent. For example, if you use a Japanese speaker and continue speech in English, the model may tend to use a Japanese accent.

Multilingual Application

It is recommended to create a speaker profile in the language you intend to use. This helps achieve the best results in that specific language, including tone, accent, and linguistic features.

While the model supports cross-lingual speech, it still relies on the reference speaker. If the speaker has a distinct accent—such as British English—other languages may carry that accent as well.

Optimal Audio Length

• Best Performance: Generate audio around 42 seconds in a single run (approximately 8,192 tokens). It is recomended not to near the limits of this windows when generating. Usually, the best results are up to 7,000 tokens.
• Context Reduction with Speaker Reference: If the speaker reference is 10 seconds long, the effective context is reduced to approximately 32 seconds.

Temperature Setting Recommendations

Testing shows that a temperature of 0.4 is an ideal starting point for accuracy (with the sampling settings below). However, some voice references may benefit from higher temperatures for enhanced expressiveness or slightly lower temperatures for more precise voice replication.

Verifying Speaker Encoding

If the cloned voice quality is subpar, check the encoded speaker sample.

interface.decode_and_save_speaker(speaker=your_speaker, path="speaker.wav")

The DAC audio reconstruction model is lossy, and samples with clipping, excessive loudness, or unusual vocal features may introduce encoding issues that impact output quality.

Sampling Configuration

For optimal results with this TTS model, use the following sampling settings.