AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.632 per minute of source video
ElevenLabs' dubbing model that generates localized voiceovers in 90+ languages and syncs them to video automatically.
Most dubbing tools support 10 to 20 languages.
ElevenLabs Dubbing doesn't just translate words.
The model generates dubbed audio that's phrase-matched to the original speech timing, and Craze's lip sync automatically adjusts mouth movements to the new audio.
Traditional dubbing requires hiring native speakers in each market.
Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| ElevenLabs DubbingElevenLabs | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | — | Up to 1080p | Up to 4K | Up to 720p |
| Length | — | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | — | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.632 per minute of source video | $0.114 per second of video | $0.075 per second of video | $0.06 per second of video |
| Task | Inputs | Resolution | Aspect ratios | Sound |
|---|---|---|---|---|
| Dubbing | Video | Follows the source | Follows the input | None |
| Dubbing | Audio | Follows the source | Follows the input | None |
$0/ month
$19/ month
$59/ month
$199/ month
ElevenLabs Dubbing handles the entire localization problem in one pass. Source video in, dubbed video in 90+ languages out. Traditional dubbing requires hiring voice actors in each market, recording separate sessions, and manually syncing lip movements. ElevenLabs Dubbing automates all of it while preserving tone and emotion.
Most dubbing tools support 10 to 20 languages. ElevenLabs Dubbing covers 90+. That reach means one video can go global without waiting for separate dubbing sessions in each language.
ElevenLabs Dubbing doesn't just translate words. It analyzes the emotional intent of the original speaker and transfers that tone into the target language. A somber moment stays somber. An energetic delivery stays energetic.
The model generates dubbed audio that's phrase-matched to the original speech timing, and Craze's lip sync automatically adjusts mouth movements to the new audio. The result looks like the speaker is actually saying the dubbed version.
Traditional dubbing requires hiring native speakers in each market. ElevenLabs Dubbing generates all voiceovers. That eliminates scheduling, talent costs, and the need to build voice talent relationships in every language.
Generate dubs in all 90+ languages without repeating the upload or re-processing. Craze handles the full workflow in one pass.
ElevenLabs Dubbing is a transform model: upload your video and choose target languages, and Craze generates dubbed versions with lip sync.
ElevenLabs Dubbing works well on videos with clear speech and audible dialogue. Background music or ambient sound is preserved, with the dubbed voiceover mixed over it.
ElevenLabs' technology delivers one key advantage over traditional dubbing: tone transfer. The model analyzes the emotional intent and delivery style of the original speaker and applies it to the target language. A joke stays funny even when dubbed into a different language. A somber moment stays somber. That emotional continuity is often lost in traditional dubbing where voice actors work from scripts without the nuance of the original performance.
ElevenLabs Dubbing is priced by the length of your source video at $0.632 per minute of source video. You pay once per source video, regardless of how many languages you dub into. A 2-minute video costs the same whether you generate 1 dub or 90.
Language count, video resolution, and audio quality don't change the price. Only the duration of the source video matters.
ElevenLabs Dubbing handles both speech synthesis and lip sync in one pass. Lip-sync-only models like Sync Lipsync 3, Kling LipSync, and LatentSync require you to provide the dubbed audio separately. ElevenLabs Dubbing generates the audio and syncs it in a single workflow.
Filmmakers, studios, and content producers can reach worldwide audiences without managing separate dubbing productions. YouTube creators, streaming platforms, and production companies all benefit from instant multilingual reach.
Companies with global customers need to localize product demos, tutorials, and marketing videos. ElevenLabs Dubbing makes it practical to do that on a tight schedule and budget.
Online course creators, universities, and educational platforms can dub courses into multiple languages. Students get instruction in their native language without sacrificing production quality.
Platforms hosting user-generated content can offer creators dubbing as a feature. Video creators get access to global audiences without managing dubbing themselves.
News organizations and journalists can localize breaking news and investigative documentaries for worldwide distribution faster than traditional dubbing allows.
Companies with global teams can dub internal communications, training videos, and company announcements into multiple languages automatically.
Dubbing into multiple languages makes content accessible to non-English speakers globally, removing language barriers to content discovery and learning.
Large events, conferences, and webinars can use ElevenLabs Dubbing to reach international audiences immediately. Instead of waiting for traditional dubbing or subtitle translation, generate dubs in key markets in minutes, making content immediately available to speakers' families, partners, and fans worldwide.
Hand Craze your video and audio and say what you want, and it runs ElevenLabs Dubbing for you. Every Craze plan, including Free, runs ElevenLabs Dubbing and every other media model, and Craze can use a different one for each job. Each video lands on an editable timeline with your cuts, captions and music, ready to export as MP4. Generations come out of your plan's monthly credits, from $0.632 per minute of source video, with top-ups when you need more.
Global content creators and studios: Filmmakers, studios, and content producers can reach worldwide audiences without managing separate dubbing productions. SaaS and product marketing: Companies with global customers need to localize product demos, tutorials, and marketing videos. Educational content: Online course creators, universities, and educational platforms can dub courses into multiple languages. Streaming and video platforms: Platforms hosting user-generated content can offer creators dubbing as a feature.
ElevenLabs Dubbing is a speech-to-speech model that generates dubbed audio in 90+ languages and automatically syncs it to video. It preserves the speaker's tone and emotional intent while translating into target languages.
ElevenLabs Dubbing costs $0.632 per minute of source video on Craze. Longer videos cost more. Use the cost calculator on this page for exact pricing.
every Craze plan, including Free include ElevenLabs Dubbing. Your plan provides monthly credits for dubbing generations.
ElevenLabs announced Dubbing v2 on May 28, 2026, initially available through ElevenCreative and ElevenProductions. The API became available in August 2026.
ElevenLabs Dubbing supports 90+ languages. The model works across diverse language families and preserves tone across all of them.
Yes. ElevenLabs Dubbing generates dubbed audio and automatically syncs the video's lip movements to the new audio. No separate lip sync step is required.
Yes. The model preserves tone and emotional intent from the original speaker, transferring that emotional quality into the dubbed language.
Craze accepts source video up to 3 hours long with ElevenLabs Dubbing, and the price follows its length.
ByteDance Seed Team
From $0.114 per second of video
ByteDance Seed Team
From $0.075 per second of video
ByteDance Seed Team
From $0.06 per second of video
