Full dubbing (see dub-video) clones the original voice's delivery and, with the HeyGen engine, lip-syncs the video. Sometimes you just need the spoken content translated — dub_video's translate_audio_only parameter is the lighter-weight version of the same tool for that case.
It's the same underlying tool as dubbing, so the same source constraints apply: media must already be Versely-hosted, and the job runs asynchronously via project_id + get_dub_status polling.
Powered by
Dub a video or audio file into another language — full AI dubbing (voice cloning + optional lip-sync), not simple TTS narration. Source must already be Versely-hosted media (a URL from a prior generation, upload, or output — e.g. *.versely.studio); external links (YouTube etc.) aren't supported yet. Runs asynchronously: submits the job and returns a project_id — poll get_dub_status or check list_dubs for completion, don't wait in this turn. Two engines: 'elevenlabs' (default, audio-cloning dub, works on audio or video, supports trimming via start_time/end_time, up to 30 min) and 'heygen' (video-only, lip-synced translation, up to 8 min, no trimming, and only supports a subset of languages).
What to tell the agent
Versely's agent maps this plain-English request directly onto dub_video. You don't need to know the parameter names — just describe what you want.
“Translate the audio in this video into French — audio translation only, don't need lip-sync.”
How it works
1. Confirm your source
The source media must already be Versely-hosted (a prior generation, upload or output URL) — external links aren't supported.
2. Set target_lang and translate_audio_only
Point target_lang at the destination language and set translate_audio_only to skip the full voice-cloned dub pipeline.
3. Choose source_lang if needed
Specify source_lang explicitly if you don't want the engine auto-detecting the spoken language.
4. Poll for the result
Like a full dub, this runs async — poll get_dub_status with the returned project_id until it reports completed.
What it costs
Cost scales with video length like a standard dub job. Use estimate_cost in chat to confirm the exact price before submitting, and check_credits to verify your balance covers it.
The formula behind that number: What does dubbing one video into 10 languages cost? — bills one flat charge per job and ignores the target language entirely.
Limits & things to know
- Source must be Versely-hosted already — YouTube links and other external URLs aren't supported as input.
- This is still the dub_video tool under the hood — it inherits the same per-engine time caps (30 min ElevenLabs, 8 min HeyGen) and async job model.
- It won't reposition or re-time visuals — this is purely an audio/language operation.
Who uses this
- Quick localization for internal review before a full dub
- Making a clip understandable to a non-native-speaking team
- Translating narration for a course draft
- Prepping subtitle-source text for a different market
Frequently asked questions
How is this different from dubbing a video?+
It uses the same dub_video tool but with translate_audio_only set, which skips the full voice-cloned, engine-choice dub pipeline in favor of a lighter audio translation. For full voice cloning and optional lip-sync, use dub-video instead.
Do I need to specify the source language?+
You can pass source_lang explicitly, or let the engine detect it automatically if you leave it unset.
Can I use this on a video from another platform?+
No — the source has to already be hosted on Versely (from a prior generation, upload, or output). Download and re-upload it first if it lives elsewhere.
Related Versely tools
Related editing jobs
Translate a Video Into Another Language inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.