Srt-AI-Voice-Assistant  by YYuX-1145

AI-powered subtitle dubbing and audio processing

Created 2 years ago
250 stars

Top 100.0% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

This project addresses the need for efficient subtitle dubbing and related media processing tasks. It offers a user-friendly, local web interface for generating voiceovers using multiple Text-to-Speech (TTS) engines, translating subtitles, and transcribing audio/video content. The primary benefit is a streamlined, customizable workflow for content creators and localization teams, enabling local execution and LAN accessibility.

How It Works

The core of Srt-AI-Voice-Assistant is its integration with various AI-TTS engines, including popular options like BV2, GSV, CosyVoice2, and AzureTTS, with extensibility for custom APIs. It presents a Gradio-based web UI for intuitive operation, supporting batch processing, subtitle editing, and regeneration of specific lines. Auxiliary functions like audio/video transcription and subtitle translation are also integrated, providing a comprehensive media processing pipeline.

Quick Start & Requirements

  • Installation involves cloning the repository (git clone https://github.com/YYuX-1145/Srt-AI-Voice-Assistant.git), navigating into the directory, installing dependencies (pip install -r requirements.txt), and running the application (python Srt-AI-Voice-Assistant.py).
  • Users must prepare their desired TTS engines separately.
  • Optional command-line arguments allow customization of server port (-p), LAN access (--lan), disabling extensions (--no_ext), creating shareable links (--share), and activating server mode (--server_mode).
  • Windows users can opt for a packaged version or an integrated package with GPT-SoVITS.
  • Documentation is available for writing extensions for unsupported TTS engines.

Highlighted Details

  • Supports multiple AI-TTS engines (BV2, GSV, CosyVoice2, AzureTTS) and custom API integration.
  • Features a friendly, locally runnable WebUI accessible via LAN.
  • Includes batch processing, subtitle editing, translation, and line regeneration capabilities.
  • Offers extended functions like audio/video transcription and multi-speaker dubbing.

Maintenance & Community

The project directs users to its "Issues" section for problem reporting and feature requests. No specific details regarding core maintainers, community channels (like Discord/Slack), or a public roadmap are provided in the README.

Licensing & Compatibility

The README does not explicitly state the project's license type or provide information regarding compatibility for commercial use or linking with closed-source projects.

Limitations & Caveats

Users are required to set up and manage their TTS engines independently. The README notes that the packaged version included in the GPT-SoVITS integrated package may not always be the latest version and might require overwriting. The absence of explicit licensing information could pose a barrier to commercial adoption or integration.

Health Check
Last Commit

2 months ago

Responsiveness

Inactive

Pull Requests (30d)
0
Issues (30d)
1
Star History
5 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.