OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Auto Synced Translated Dubs

Auto Synced Translated Dubs is a Python application that translates text from an existing SRT subtitle file and uses text-to-speech to assemble a dubbed audio track aligned to the subtitle timings.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Auto Synced Translated Dubs — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you have a source video and human-made SRT subtitles and want translated subtitle files plus speech aligned to the subtitle cue timings.

Who it is for

  • Video creators preparing translated subtitle and voice tracks from existing SRT files.
  • Users who want to configure languages, voices and translation choices for repeatable or batch dubbing.

Documented uses

  • Translate subtitle text and generate corresponding SRT files.
  • Create speech clips for translated subtitle cues and assemble them into a timed audio track.
  • Process several configured languages in sequence.
  • Use separate utilities to add language audio tracks to an MP4 or translate YouTube titles and descriptions.
Before you choose

Requirements & limits

The project is a public GitHub repository licensed under AGPL-3.0. It requires local setup and credentials for selected third-party translation and text-to-speech services.

  • Translation options include Google Cloud and DeepL; speech synthesis options listed in the README include Google, Azure and ElevenLabs.
  • Audio timing can use duration adjustment or a second synthesis pass; Azure TTS can specify the desired duration during synthesis.
  • The application assumes one speaker, though separate SRT files can be used to create separate tracks.
  • FFmpeg is required; Rubber Band is described as an optional alternative for audio stretching.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Configure the application for a dubbing run

Prepare the application, service credentials and language settings for a run using an existing video and SRT file.

Before you start

  • Python; the README says the project was written using Python 3.9.
  • FFmpeg installed.
  • Google Cloud, Azure and/or DeepL credentials for the services selected.
  • A source video and a human-made SRT subtitle file.

Steps

  1. Download or clone the repository and install its requirements with the command below.

    Documented command
    pip install -r requirements.txt

  2. Install FFmpeg and enter the selected translation and text-to-speech service credentials in cloud_service_settings.ini.

  3. Review config.ini for synthesis and translation options.

  4. Set the source video and subtitle paths in batch.ini, then configure enabled languages and their voices.

Expected outcome

The configuration is prepared to run the application on the selected video, subtitle file and languages.

Guide limitations

  • The README directs users to check each service's documentation for supported languages and voices.
  • This recipe covers setup; it does not verify a run or guarantee compatibility.
  • The application assumes one speaker unless separate SRT files are prepared for individual speakers.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
3 November 2026
Original website title
ThioJoe/Auto-Synced-Translated-Dubs · Official homepage title · retained in its source language
How we review sourcesSuggest a correction