Srt-AI-Voice open source subtitle dubbing tool

By /

Srt-AI-Voice-Assistant uses multiple AI-TTS to dub your subtitles or text files. It also provides a variety of convenient auxiliary functions including subtitle recognition and translation.

by .srt Subtitle files are combined with multiple AI text-to-speech (TTS) engines to automatically generate dubbing tracks for subtitles, realizing integrated subtitle/dubbing processing

Project introduction and core functions

🎙Core positioning

  • Subtitle dubbing assistant: The main thing is to dub audio and video content through subtitle files, especially suitable for scenes that require dubbing sentence by sentence, such as video commentary, dubbing of ghosts and animals, etc.

The main integrated functions include:

  • Supports multiple AI‑TTS engines (such as BV2, CosyVoice2, GSV, AzureTTS) and allows users to customize API access
  • Supports advanced features such as multi-role dubbing, batch mode, and single-sentence re-drawing (that is, recreating a certain speech sentence)
  • The ability to edit and translate subtitle text, you can modify or translate SRT and re-import it into the dubbing process
  • Supports transcription of audio and video files to generate subtitles, and synchronous output of subtitles and audio tracks

🛠Experience and installation process

  • Supports graphical WebUI interface, runs locally and supports local area network access, allowing users to operate without writing code
  • Provide Standalone package (packaged version) and GPT ‑ SoVITS integrated package (provided by Hugging Face) for easy use by Windows or users who cannot successfully install and rely on it
  • The installation process usually involves installing dependencies (requirements.txt) in the Python environment, and then running scripts such as Srt‑AI‑Voice‑Assistant.py Start it; you can also use double click .bat Quick operation

The functional flow is roughly as follows

  1. Users provide videos or have existing videos .srt Subtitle files;
  2. Item Match caption sentence by sentence Timeline;
  3. Call the selected AI‑TTS engine to generate corresponding speech;
  4. Support listening, editing and recreating a certain sentence;
  5. synthesize a final audio track and output it synchronously with that corresponding Timeline of the video;
  6. Support translation, generation of new subtitles and export of dubbing files.

ˇ Suggestion of usage scenarios️

  • Video producers want to quickly generate AI dubbing for subtitles, especially for multiple characters (character dubbing recognition);
  • Want to process multiple batches .srt File and output voice;
  • If you want to integrate AI dubbing into your own process, you can customize the access API;
  • Users who need subtitle translation, editing, and one-click re-dubbing.

丨ˇ Summary

“Srt‑AI‑Voice‑Assistant“is a feature-rich and flexibly configured subtitle and dubbing integration tool that supports local operation, Web UI operations, multiple TTS access, multi-role dubbing, subtitle translation and editing, and batch processing capabilities. If you need to quickly add personalized dubbing to subtitles and want to visualize and customize access interfaces, this project is a great fit.

Github：https://github.com/YYuX-1145/Srt-AI-Voice-Assistant

Experience:https://srt-ai-voice-assistant-onlinedemo.work

Oil tubing:

Scroll to Top