
Security News
npm ‘is’ Package Hijacked in Expanding Supply Chain Attack
The ongoing npm phishing campaign escalates as attackers hijack the popular 'is' package, embedding malware in multiple versions.
A powerful command-line interface for Chatterbox TTS - Resemble AI's state-of-the-art open-source Text-to-Speech model.
# Install core dependencies
pip install chatterbox-tts torch torchaudio
# Install optional audio playback libraries
pip install pygame playsound
# Or install all dependencies at once
pip install -r requirements.txt
# Install from PyPI (once published)
pip install voice-forge
# Or install from source
pip install -e .
# Or run directly from the package
python -m voice_forge --help
# Generate and play speech from text
voice-forge "Hello, world! This is Voice Forge with Chatterbox TTS."
# Save audio to file
voice-forge "Hello, world!" --save output.wav
# Read text from file
voice-forge --file input.txt --save output.wav
# Use a reference voice
voice-forge "Hello, world!" --voice reference.wav
# Combine voice cloning with file output
voice-forge "Hello, world!" --voice reference.wav --save cloned_output.wav
# Adjust exaggeration and CFG weight
voice-forge "Hello, world!" --exaggeration 0.7 --cfg-weight 0.3
# Use CPU instead of GPU
voice-forge "Hello, world!" --device cpu
# Save without playing
voice-forge "Hello, world!" --save output.wav --no-play
# Use specific audio backend
voice-forge "Hello, world!" --audio-method pygame
voice-forge "Hello, world!" --audio-method playsound
voice-forge "Hello, world!" --audio-method system
Option | Short | Description | Default |
---|---|---|---|
text | - | Text to convert to speech | - |
--file | -f | Read text from file | - |
--voice | -v | Path to reference audio file for voice cloning | - |
--exaggeration | -e | Exaggeration/intensity control (0.0-1.0) | 0.5 |
--cfg-weight | -c | CFG weight for generation control (0.0-1.0) | 0.5 |
--save | -s | Save generated audio to file | - |
--no-play | - | Don't play audio, only save to file | False |
--audio-method | - | Audio playback method (auto/pygame/playsound/system) | auto |
--device | - | Device to run model on (auto/cpu/cuda) | auto |
--verbose | -V | Enable verbose output | False |
voice-forge "Welcome to Voice Forge with Chatterbox TTS!"
voice-forge "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill."
voice-forge "This is amazing!" --exaggeration 0.8 --cfg-weight 0.2
voice-forge "Hello, this is my cloned voice!" --voice my_voice_sample.wav
# Create a text file with your content
echo "This is a longer text that I want to convert to speech." > input.txt
voice-forge --file input.txt --save batch_output.wav
exaggeration=0.5
, cfg_weight=0.5
) work well for most promptscfg_weight
to around 0.3
cfg_weight
values (e.g., ~0.3
) and increase exaggeration
to around 0.7
or higherexaggeration
tends to speed up speech; reducing cfg_weight
helps compensate with slower, more deliberate pacingIf you encounter import errors:
# Make sure all dependencies are installed
pip install chatterbox-tts torch torchaudio pygame playsound
# On macOS, you might need:
pip install torch torchaudio --index-url https://download.pytorch.org/whl/cpu
If audio doesn't play:
# Try different audio methods
voice-forge "test" --audio-method system
voice-forge "test" --audio-method pygame
voice-forge "test" --audio-method playsound
# Or just save to file and play manually
voice-forge "test" --save test.wav --no-play
If you have CUDA issues:
# Force CPU mode
voice-forge "test" --device cpu
This project is based on Chatterbox TTS by Resemble AI, which is licensed under the MIT License.
Contributions are welcome! Please feel free to submit a Pull Request.
This tool is for educational and research purposes. Please use responsibly and follow all applicable laws and ethics guidelines when generating synthetic speech.
FAQs
A command-line tool for text-to-speech generation using Chatterbox TTS
We found that voice-forge demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
The ongoing npm phishing campaign escalates as attackers hijack the popular 'is' package, embedding malware in multiple versions.
Security News
A critical flaw in the popular npm form-data package could allow HTTP parameter pollution, affecting millions of projects until patched versions are adopted.
Security News
Bun 1.2.19 introduces isolated installs for smoother monorepo workflows, along with performance boosts, new tooling, and key compatibility fixes.