Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.dubformer.ai/llms.txt

Use this file to discover all available pages before exploring further.

The Platform API provides direct access to Dubformer’s video dubbing capabilities with full control over processing parameters. Perfect for developers building applications that need automated video localization.

​
Base URL

https://app.dubformer.ai/api/v1

​
Key Features

​
🎯 Direct Video Processing

Submit video URLs and receive dubbed videos without intermediate steps.

​
🎭 Advanced Voice Control

  • Choose specific voices from our voice library
  • Use soundalike voices for natural results
  • Enable emotional transfer for expressive dubbing

​
🔊 Flexible Audio Mixing

  • Voiceover Only: Clean dubbed audio track
  • Voiceover with Original: Blend dubbed and original audio
  • Smart Vocal Removal: Replace original speech while preserving background audio

​
📝 Custom Content Support

  • Provide custom transcriptions
  • Upload translation glossaries
  • Fine-tune timing and speaker assignments

​
What You Can Do

  1. Create Dubbing Projects - Submit videos with target language and preferences
  2. Monitor Progress - Track processing status in real-time
  3. Download Results - Get dubbed video files and audio tracks
  4. Modify and Re-translate - Update translations and regenerate audio
  5. Manage Projects - List, update, and delete your projects

​
Core Concepts

​
Projects

A project represents a single video dubbing task with specific source and target languages.

​
Speakers

Each speaker in the video can be assigned different voices and styles (masculine/feminine).

​
Mixing Modes

Control how the dubbed audio is mixed with the original video:
  • voiceover_only - Only the dubbed voice
  • voiceover_with_original_track - Dubbed voice + original audio
  • voiceover_without_original_voice - Dubbed voice + background audio only

​
Voice Types

  • Standard voices - High-quality TTS voices
  • Soundalike voices - AI-generated voices that match original speaker characteristics
  • Emotional transfer - Advanced soundalike with emotional expression

​
Supported Languages

The Platform API supports:
  • 40+ source languages for speech recognition
  • 100+ target languages with locales for dubbing
  • Popular combinations like EN→ES, EN→FR, ES→EN, etc.
Use the Get Options endpoint to retrieve the full list.

​
Pricing Model

Projects are billed based on video duration:
  • Charged per minute of processed video
  • Different rates for standard vs. soundalike voices
  • Check your balance with the Get Balance endpoint