ElevenLabs Dubbing
ElevenLabs Dubbing and Voice Translation is an AI tool designed to facilitate dubbing and voice translation of videos in multiple languages...
Last verified:
What is ElevenLabs Dubbing?
ElevenLabs Dubbing is an AI-powered audio and video translation tool that localizes content across 90+ languages while preserving the original speaker's voice, emotion, timing, and tone. The tool automatically separates each speaker's dialogue from the soundtrack, detects multiple speakers even with overlapping speech, and recreates the original delivery in another language. It supports uploading video/audio files directly or pasting URLs from YouTube, TikTok, Vimeo, X, and other platforms.
Key features include Dubbing v2 Alpha (the latest model conditioning on source performance rather than transcript for authentic localization), automatic voice cloning that creates a model of the original speaker and applies it across all target languages, and sync-aware translation logic that aligns starts and stops with the original out of the box. The tool offers Automatic Dubbing for one-click localization with upload limits up to 2 GB and 180 minutes, plus Dubbing Studio for granular control over transcripts, translation, timing, speaker reassignment, and per-clip regeneration (though Dubbing Studio is in maintenance mode with V1 model only, limited to 1 GB and 45 minutes).
ElevenLabs Dubbing is designed for creators, marketers, studios, broadcasters, and teams who want to expand their audience to international markets without re-recording voice talent. It helps grow addressable audience by 4x, adapt existing material for new markets while preserving emotional nuance, and offers a fully managed dubbing service via ElevenLabs Productions for broadcast-quality requirements with human translators and expert voice casting.
The tool supports 90+ languages including English, Spanish, French, German, Japanese, Chinese, Arabic, and more. It preserves the speaker's identity, pitch, and tonality across all target languages, keeps background audio without re-mixing music or effects, and supports up to 9 unique speakers per file for best quality. All self-serve plans allow up to 5 concurrent dubbing jobs.
ElevenLabs Dubbing pricing
Pricing model: Freemium
ElevenLabs uses a credit-based subscription model. Free tier: $0/month with 10k credits/month, includes Text to Speech, Speech to Text, Sound Effects, Voice Design, Music, Productions, Image & Video, 3 Projects in Studio, but dubbing is watermarked. Starter: $6/month with 30k credits/month, includes Dubbing Studio, Instant Voice Cloning, 20 Projects in Studio, Commercial License. Creator (popular): $11/month (first month 50% off from $22) with 121k credits/month, includes Professional Voice Cloning, removes watermark from dubbing. Pro: $99/month with 600k credits/month, includes 44.1kHz PCM audio output via API, 192kbps quality audio. Scale: $299/month with 1.8M credits/month, includes 3 workspace seats, team collaboration, 3 Professional Voice Clones. Business: $990/month with 6M credits/month, includes 10 seats, 10 Professional Voice Clones, low-latency TTS. Enterprise: custom pricing with custom credits/seats, fully managed dubbing with Productions, elevated concurrency, priority support. Dubbing v2 priced per minute in USD on Automatic Dubbing. Watermarked cost: 2000 credits/min, non-watermarked: 3000 credits/min. Overages cost $0.54–$0.90/min depending on tier.
ElevenLabs Dubbing pros
- Preserves original speaker's voice identity, pitch, and tonality across all languages
- Supports 90+ languages and accents for global localization
- Automatic speaker separation detects multiple speakers even with overlapping speech
- Dubbing v2 conditions on source performance, not transcript, for authentic emotion transfer
- One-click automatic dubbing requires no setup or pipeline building
- Sync-aware translation aligns dialogue starts and stops with original video
- Keeps background audio, music, and effects without re-mixing
- Upload limits up to 2 GB and 180 minutes for Automatic Dubbing
- Supports URLs from YouTube, TikTok, Vimeo, X, and direct file uploads
- Voice cloning is fully automatic with no manual setup required
- Localizes content by adapting phrasing for native speaker naturalness, not literal translation
- Dubbing Studio offers transcript editing, speaker reassignment, and per-clip regeneration
- Up to 5 concurrent dubbing jobs on all self-serve plans
- Failed dubbing jobs on Dubbing v2 are not charged
- Professional-quality output at a fraction of traditional dubbing cost
ElevenLabs Dubbing cons
- Dubbing v2 API not yet live, only coming soon to select enterprise customers
- Dubbing Studio is in maintenance mode with V1 model only and critical bug fixes only
- Free-tier dubs are automatically watermarked, only Creator+ plans remove watermark
- Dubbing v2 in alpha may have occasional rough edges as model improves
- Realtime or live dubbing not currently available
- Dubbing Studio limited to 1 GB and 45 minutes upload, much less than Automatic Dubbing
- Higher cloning strength settings can sound less natural across phonetically different languages
- No watermark-for-credit-discount option on Dubbing v2 like legacy V1 had
Frequently asked questions about ElevenLabs Dubbing
Is realtime or live dubbing available?
Realtime or live dubbing is not currently available. The tool processes uploaded audio and video files asynchronously, and you will be shown the cost and asked to confirm your request before submission. Once the dub is ready, you can download it from your list of dubs.
What happens if my dub fails or gets stuck?
If a Dubbing Studio job fails or you cancel it, the credits are automatically refunded to your account. Dubbing v2 (priced per minute in USD on Automatic Dubbing) is not charged for failed jobs. If a dub is stuck in Queued or Loading for an extended period, cancel and resubmit it. You will not lose credits by doing so.
Is Dubbing v2 available via API?
The Dubbing v2 API is not yet live but is expected to launch in the coming weeks. Currently, API access is coming soon to select enterprise customers. You need to reach out to the sales team to learn more. Self-serve API access is not yet available.
How do I use the legacy V1 dubbing model?
Automatic Dubbing on the main Dubbing page uses Dubbing v2 by default. To use the legacy V1 dubbing model and the original dubbing dialog, click Advanced and then Use Legacy V1 Dubbing Model. The legacy dialog includes the V1 watermark-for-credit-discount option and is the only way to reach Dubbing Studio from this page. Note that Dubbing Studio is only available via the V1 model and is in maintenance mode.
What languages does ElevenLabs Dubbing support?
ElevenLabs Dubbing supports 90+ languages including English, Spanish, French, German, Japanese, Chinese, Arabic, and more. This enables localization for international audiences across a wide range of language pairs. The tool adapts phrasing and meaning so the output sounds natural to native speakers rather than producing literal word-for-word translations.
How does the cloning strength setting work?
Cloning strength is the configurable setting in Automatic Dubbing on the Dubbing v2 Alpha model. The default value of 7 works well for most content. Higher values prioritize voice similarity to the original speaker, which can sound less natural across languages with very different phonetic characteristics. A higher setting can also carry over more of the original accent into the dubbed output. Lower values give the model more freedom for natural delivery in the target language at the cost of resemblance to the original voice.
What are the upload limits for dubbing?
Automatic Dubbing powered by Dubbing v2 Alpha has upload limits up to 2 GB and 180 minutes. Dubbing Studio (V1 model only) has upload limits up to 1 GB and 45 minutes. The API supports files up to 1GB and 2.5 hours. For best quality, up to 9 unique speakers per file is recommended. All audio and video content types are supported.
Can I remove the watermark from dubbed videos?
Free-tier dubs are watermarked automatically. Paid-tier dubs are not watermarked. Dubbing without a watermark is only available for Creator+ users (Creator, Pro, Scale, Business, Enterprise plans). There is no watermark-for-credit-discount option on Dubbing v2. The legacy V1 dubbing flow and Dubbing Studio were the only places where the watermark discount existed. Watermarks are only available for video dubs, not audio.
How many concurrent dubbing jobs can I run?
All self-serve plans (Free, Starter, Creator, Pro, Scale, Business) allow up to 5 concurrent dubbing jobs. Enterprise plans default to 100 concurrent dubbing jobs. If you hit the limit, you will receive a too_many_concurrent_requests error and should wait for existing jobs to complete before starting new ones.
What file types and sources does dubbing support?
Videos and audio can be dubbed from various sources including YouTube, X (Twitter), TikTok, Vimeo, direct URLs, or direct file uploads. All audio and video content types are supported. You can upload your video or audio file directly, or select the Paste URL tab to dub a video from supported platforms. The tool accepts raw video files, finished exports, and standalone audio files.