ElevenLabs Dubbing (v2)
End-to-end dubbing that transcribes, translates and regenerates speech in the source speaker's voice across 90+ languages, with dialect variants in v2. It detects multiple speakers including overlapping speech and can retain background audio.
- Up to
- 10800 seconds
- Weights
- Not released
- API
- Yes
- Commercial use
- Permitted subject to conditions
A legacy Dubbing Studio interface adds transcript editing and per-clip regeneration but is in maintenance mode.
Standard ElevenLabs terms: commercial use on paid plans, non-commercial on free.
- The free tier is non-commercial. Standard ElevenLabs terms: commercial use on paid plans, non-commercial on free
- Depends on your plan tier. Standard ElevenLabs terms: commercial use on paid plans, non-commercial on free
- Output is watermarked. Dubbing v1 has a watermarked cheaper tier
- Requires consent from the person depicted. Dubbing reproduces the original speakers' voices, so you need rights/consent from the on-screen talent independently of ElevenLabs' terms
Specification
- What it takes in
- audio, video
- What it makes
- audio, video
- Maximum duration
- 10800 seconds
- Controls
- voice-cloning, multi-speaker-dialogue, timestamps
- Weights
- Not released
- API
- Yes
- Pricing
- Per the API pricing page: Dubbing v2 end-to-end $2.20 per minute across 92 languages; Dubbing v1 $0.33 per minute with watermark or $0.50 per minute without.
- Released or updated
- not established
- Languages
- 92, not individually listed by the vendor
Strengths
- Up to 180 minutes / 1GB per job in the app and 3GB per file via API
- Up to 32 unique speakers detected per file, including overlapping speech
- Keeps background audio without a full re-mix
- Adjustable voice-cloning similarity (0-10)
Weaknesses
- v2 at $2.20/min is far more expensive than v1
- No lip-sync feature documented
- Dubbing Studio (the granular editing UI) is v1-only and in maintenance mode
- Only 3 concurrent dubbing jobs on self-serve plans (10 on Enterprise)
Best for
- localising finished video
- multi-speaker interview dubbing
- reaching additional language markets
Where the sources disagree
Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.
- Docs say '90+ languages'; the API pricing page says Dubbing v2 covers 92 languages.
MCP servers that front ElevenLabs
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
ElevenLabs
ElevenLabs MCP server: TTS, music, sound effects, voices, and audio transcription.
-
Elevenlabs
RunAPI MCP server for ElevenLabs: create tasks, poll status, check pricing.
-
Elevenlabs
Convert text to speech, transcribe audio, and dub videos with AI voices.
-
Jellypod
Create, import, and publish Jellypod podcast episodes from your AI assistant.
-
Labs
MCP Server with AI-powered tools including ElevenLabs text-to-speech for realistic voice synthesis.
-
Picsart GenAI
Generate and edit images, videos and audio with 150+ AI models.
See it from the vendor
Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.
Nearby in the directory
ElevenLabs Agents
A hosted conversational voice stack that chains a fine-tuned speech-to-text model, a selectable LLM, low-latency TTS and a proprietary turn-taking mod
Voice and speech
Eleven v3
ElevenLabs' most expressive text-to-speech model, aimed at emotionally varied narration rather than lowest latency. It supports natural multi-speaker
Voice and speech
Eleven Flash v2.5
The low-latency ElevenLabs model, documented at roughly 75ms model latency with a 40,000-character request limit. It covers 32 languages and is priced
Voice and speech