ElevenLabs
AI Services Available Requires secrets

ElevenLabs — AI Voice Synthesis & Dubbing

Generate multilingual dubbed audio tracks automatically with ElevenLabs in Enveu Flow. Integrate AI voice dubbing into your media operations pipeline.

What this integration does

Generate multilingual dubbed audio tracks automatically with ElevenLabs in Enveu Flow. Integrate AI voice dubbing into your media operations pipeline.

Best for

Generating dubbed audio tracks in multiple languages from source transcripts for multilingual content delivery without manual voice recording.

Generate high-quality dubbed audio tracks in multiple languages using ElevenLabs AI voice synthesis. Use in Auto Multi-Audio workflows to automatically produce localised audio versions of your video assets on approval.

Inputs & outputs.

Inputs
Source transcript Time-coded text transcript from transcription step
Target language Language code for the dubbed output
Voice profile Configured voice ID for the target language
Outputs
Dubbed audio file MP3 or WAV audio track in the target language
Audio duration Duration of the generated audio file in seconds

Triggers & actions.

Triggers
Transcript ready
Fires when an upstream transcription step outputs a time-coded transcript
Asset approved
Asset status changes to approved in CMS triggering dubbing workflow
Actions
Text to speech
Convert text to a natural-sounding audio track
Dub audio
Generate a dubbed audio track from a source audio file in a target language
List voices
Fetch available voice options for your account
Clone voice
Create a custom voice clone from a reference audio file

Example workflow.

Asset approved
CMS trigger
Transcribe audio
Gladia
Dub to target language
ElevenLabs
Attach audio track
CMS or MAM
Notify
Slack

Used in these workflows.

Frequently asked questions.

ElevenLabs supports 29+ languages for dubbing including Spanish, French, German, Portuguese, Italian, Polish, Hindi, Japanese, Korean, and more. Available languages depend on your ElevenLabs subscription plan.
Yes. ElevenLabs supports voice cloning from a reference audio file. You can configure Flow to use a specific voice ID per language, maintaining a consistent presenter voice across all your dubbed content.
Flow extracts the primary audio track from your video asset or pulls a separate audio file from storage. The audio is passed to ElevenLabs with the target language configuration and the dubbed track is returned automatically.
ElevenLabs handles timing and synchronisation as part of the dubbing process. The output audio track is timed to match the original video pacing. Flow attaches the synced track to your asset record automatically.