FastDub

FastDub is a Python package and command-line utility for automated subtitle voiceovers, video dubbing, audio ducking, dynamic voice changing, subtitle translation, and YouTube integration.

Features

• Automated Video Dubbing: Generate speech from subtitle files (.srt, .vtt) and embed the audio into videos (.mp4, .mkv).
• Audio Ducking (Sidechain Compression): Dynamically lower original background audio level while speech is active.
• Dynamic Voice Changing: Switch voices mid-track using subtitle anchors (!:).
• Subtitle Translation: Auto-translate subtitles to target languages using Google Translate or alternative services.
• YouTube Integration: Download video playlists/channels, search YouTube directly from CLI, and upload dubbed videos back to YouTube with translated titles and descriptions.
• Cross-Platform: Support for SAPI voices on Windows and eSpeak/RHVoice on Linux.

Installation

System Dependencies

Ubuntu / Debian

sudo apt update -y && sudo apt upgrade -y
sudo apt install -y python3 python3-pip ffmpeg espeak libxml2-dev libxslt1-dev

macOS

brew install ffmpeg espeak

Installing FastDub

Via PyPI with pip

# Core package
pip install FastDub

# Install all optional dependencies (Translation + YouTube support)
pip install "FastDub[ALL]"

Extra Feature Bundles

Via Poetry

poetry add fastdub --extras "all"

Quick Start

Basic Local Video Dubbing

To voiceover all videos in a target directory:

fastdub -i ./input_folder -v "Yuriy" --no-sidechain -sf srt -vf mp4

Or using python module invocation:

python -m fastdub -i ./input_folder -l ru

Subtitle Translation

Translate subtitles to Russian before voice acting:

fastdub -i ./input_folder -tr -l ru -ts google

YouTube Download & Dubbing

Process a single YouTube video:

fastdub -yt -i "https://youtu.be/DD5UKQggXTc" -l ru

Process videos from a YouTube Search query:

fastdub -yt -yts -i "#python" -yts-l 5 -l ru

Process an entire YouTube channel:

fastdub -yt -i "c/UCi-5OZ2tYuwMLIcEyOsbdRA" -l ru

YouTube Upload Setup

To upload processed videos to YouTube (FastDub[YTU]):

1. Go to Google Cloud Console Credentials.
2. Create OAuth 2.0 Client ID for Desktop App.
3. Download the JSON credentials file and place it in your working directory as client_secrets.json.
4. Run FastDub with upload flags:

fastdub -i ./input_folder -ytu -ytu-ps private -ytu-t

Advanced Usage

Dynamic Voice Anchors

Change the active voice actor for specific sections by inserting anchor tokens in your subtitle file.

Example SRT subtitle content:

1
00:00:01,000 --> 00:00:04,000
!:Yuriy Hello, welcome to this video!

2
00:00:04,500 --> 00:00:08,000
!:Elena Here is the next speaker.

If voice anchors are updated and cached files need to be refreshed, clear the cache using -rc:

fastdub -i ./input_folder -rc 1

Tortoise-TTS Support

FastDub now supports Tortoise-TTS for high-quality voice cloning and text-to-speech. Tortoise generates highly realistic voices but requires significantly more processing power (CUDA is highly recommended).

1. Install with Tortoise support:

   pip install "FastDub[tortoise]"
   

2. Use the Tortoise engine: Specify --tts-engine tortoise. You can use any Tortoise voice preset (e.g., random, angie, train_atkins) as the voice argument.

   fastdub -i ./input_folder -te tortoise -v random
   

3. Tortoise Presets (Quality vs Speed): By default, FastDub uses the fast preset for Tortoise. You can change this using the --tortoise-preset argument:

   fastdub -i ./input_folder -te tortoise -tp high_quality -v angie
   

   Available presets: ultra_fast, fast, standard, high_quality.

Command Line Arguments Reference

usage: fastdub [-h] [-rc {0,1,2}] [-ra | --cleanup-audio | -n-ra | --no-cleanup-audio]
               [-ev | --export-video | -n-ev | --no-export-video] [-l LANGUAGE]
               [-ll {CRITICAL,FATAL,ERROR,WARN,WARNING,INFO,DEBUG,NOTSET}]
               [-tc THREADS_COUNT] -i INPUT [-vf VIDEO_FORMAT] [-sf SUBTITLES_FORMAT]
               [-En EXCLUDE [EXCLUDE ...]] [-Eu EXCLUDE_UNDERSCORE]
               [-sc | --sidechain | -n-sc | --no-sidechain]
               [-sc-args SIDECHAIN_FFMPEG_PARAMS] [-sc-lvl SIDECHAIN_LEVEL_SC]
               [-v VOICE] [-a ALIGN] [-v-set-a VOICE_SET_ANCHOR]
               [-fll {trace,debug,verbose,info,warning,error,fatal,panic,quiet}]
               [-y | --confirm | -n-y | --no-confirm] [-af AUDIO_FORMAT] [-wm WATERMARK]
               [-tb | --traceback | -n-tb | --no-traceback] [-yt]
               [-ak API_KEYS [API_KEYS ...]] [-yts] [-yts-l YOUTUBE_SEARCH_LIMIT]
               [-yts-rg YOUTUBE_SEARCH_REGION] [-ytu]
               [-ytu-ps {private,public,unlisted}] [-ytu-t] [-tr] [--rewrite-srt | --no-rewrite-srt]
               [-ts TRANSLATE_SERVICE]

Python API Usage

FastDub modules can be imported directly into Python applications:

from fastdub import GlobalSettings, dubber

GlobalSettings.language = "ru"
GlobalSettings.threads_count = 4

# Perform dubbing operation programmatically
dubber.dub(
    input_dir="./media",
    voice="Yuriy",
    export_video=True,
    sidechain=True
)

Development & Publishing

FastDub uses Poetry for build backend management.

Build Package

poetry build

Publish Package

poetry publish

Issues & Support

If you encounter any issues or have feature requests, please open an issue on GitHub Issues.

License

Distributed under the MIT License. See LICENSE for details.