Trusted by 1M+ creators
Dubbing API
Send a video and a target language. Get it back translated, in the speaker's own voice, with lips that match
No credit card required
4.6
2,100+ reviews
Dubbing API: Translate any video into 100 languages without reshooting
Localizing video the old way means a translator, a voice actor per language, a sound engineer, and a mouth that never quite matches. VEED's AI dubbing API does the whole job from one request. Send a video URL and a target language, and the model transcribes the speech, translates it, clones each speaker's voice, and lip-syncs the new audio to the original footage.
The result keeps the tone, emotion, and body language of the original take, so a dubbed podcast still sounds like the host, and a dubbed course still sounds like the instructor. Build it into your product or pipeline to ship YouTube videos, training content, interviews, and ads in every market you sell to. Need lip-sync for audio you already have? Use VEED's lip sync API instead.
How to dub a video with the AI dubbing API:
Step 01
Send your video and target language
Create a VEED API account, grab your key and make a request with a video URL and the language you want. Choose Standard for fast, affordable dubbing in 100 languages, or Pro for precise lip-sync, accent control, background audio, and multi-speaker videos. Videos can run up to 10 minutes.
Step 02
Let the model translate, clone, and sync
The API transcribes the speech, translates it, and generates the new track in a clone of each speaker's voice. Then it lip-syncs the footage to the translated audio, carrying the original tone, emotion, and delivery into the new language.
Step 03
Get your dubbed video back
The request returns a job you can poll. When it completes, download the finished video at the original framing, ready to publish. Pair it with VEED's subtitle API to add captions in the new language before it ships.
Learn More
Also see Fabric 1.0 – VEED’s image-to-video model:
Turn one master video into various language versions. No studio, no reshoot
Go from one master video to a dozen language versions without a studio, a casting call, or a reshoot. The dubbing API handles transcription, translation, voice cloning and lip-sync in a single job, so product teams, localization platforms, and media companies can dub a YouTube library, a course catalog, or an ad set at the pace their roadmap demands.
Dubs that sound like the speaker, with genuine emotions
Each voice is cloned from the original recording, so the translated line lands with the same tone, emotion, and pacing as the take. Pro keeps the original background audio, handles multiple speakers in podcasts and interviews, and lets you choose the target accent across 14 variants. Viewers see a video that looks like the speaker made it in their language, not a machine.
Drop it into your pipeline and dub at library scale
Run the dubbing API wherever your stack already lives, on the VEED API or through Fal, and batch it across an entire content library instead of dubbing one video at a time. Usage-based pricing means you scale output without adding seats or minimums. Chain it with VEED’s Fabric 1.0 API to generate talking videos from a single image, or VEED’s background removal API to keep every language version clean and on-brand.
FAQ
An AI dubbing API is an endpoint that takes a video and a target language and returns the same video with translated speech. VEED's version transcribes the original audio, translates it, generates the new track in a clone of each speaker's voice, and lip-syncs the footage to match. Developers call it from their own product or pipeline instead of managing translators, voice actors, and sync by hand.
Videos can run up to 10 minutes per request, which covers most ads, explainers, lessons, and podcast segments. Longer footage can be split into parts or discussed with sales. Multi-speaker videos such as interviews, panels, and two-host podcasts are supported on Pro, which clones and syncs each speaker separately so every voice stays recognizable.
Standard dubs into 100 languages. Pro dubs into 94 languages and adds 14 accent variants, so you can pick Mexican or Castilian Spanish, for example, or British or American English for the target voice. Send the base language code on Standard. On Pro, use the listed accent variants for a regional voice.
Standard costs $0.11 per second of video, and Pro costs $0.18 per second. A one-minute clip is $6.60 on Standard and $10.80 on Pro. Pricing is usage-based with no seat fees or monthly minimums, and you are billed only when a job completes. Enterprise teams with high volume can contact sales for custom pricing.
Standard is the fast, affordable option for most use cases and supports 100 languages. Pro is the recommendation when lip-sync precision matters. It adds accent control across 14 variants, keeps the original background audio, and handles multi-speaker videos such as podcasts and interviews across 94 languages. Both clone the speaker's voice and lip-sync the result.
Yes. Send the episode or video URL with the target language code, and the API returns a dubbed version with the host's cloned voice and matching lip movement. For podcasts and interviews, use Pro so each speaker keeps their own voice and the room tone stays intact. Teams use it to publish the same YouTube channel or course in Spanish, Hindi, French, and more.
Loved by creators.
Loved by the Fortune 500
“
With VEED I didn't need 15 tutorials - I jumped straight in and started editing.
Gwenne Wilcox
Founder,
Brand Brainery
“
You can go beyond choppping things. VEED actually makes my videos look great.
Michael Glover
Demand Gen Manager,
ConvertFlow
“
The first four videos i created with VEED got over 40,000 impressions on LinkedIn.
Travis Tyler
Senior Content Producer,
PandaDoc
“
I found VEED at the right time: if you're making UGC ads and not using Eye Contact Correction and Noise Reduction on VEED you're missing out on ROI.
Sebastian Schurgers
Head of Growth Marketing,
Gronda
“
With VEED I didn't need 15 tutorials - I jumped straight in and started editing.
Gwenne Wilcox
Founder,
Brand Brainery
“
You can go beyond choppping things. VEED actually makes my videos look great.
Michael Glover
Demand Gen Manager,
ConvertFlow
“
The first four videos i created with VEED got over 40,000 impressions on LinkedIn.
Travis Tyler
Senior Content Producer,
PandaDoc
“
I found VEED at the right time: if you're making UGC ads and not using Eye Contact Correction and Noise Reduction on VEED you're missing out on ROI.
Sebastian Schurgers
Head of Growth Marketing,
Gronda
“
The first four videos i created with VEED got over 40,000 impressions on LinkedIn.
Travis Tyler
Senior Content Producer,
PandaDoc
“
I found VEED at the right time: if you're making UGC ads and not using Eye Contact Correction and Noise Reduction on VEED you're missing out on ROI.
Sebastian Schurgers
Head of Growth Marketing,
Gronda
“
With VEED I didn't need 15 tutorials - I jumped straight in and started editing.
Gwenne Wilcox
Founder,
Brand Brainery
“
You can go beyond choppping things. VEED actually makes my videos look great.
Michael Glover
Demand Gen Manager,
ConvertFlow
Explore related tools
More from VEED
Launching VEED’s Lipsync API: World's Most Powerful Lip-Syncing Tech
We’re excited to introduce the VEED Lipsync API—the world’s most powerful lip-syncing technology, now available for developers and teams.
Launching VEED Fabric 1.0 API: World's First-Ever AI Talking Video Model
We’re excited to launch Fabric 1.0 API, the world’s first talking video model. It's 60x cheaper and 7x faster than comparable options. Learn more here.
Introducing Your AI Video Playground
If you’ve spent any time on LinkedIn or your favourite creator forums lately, you’ve probably seen the buzz: Minimax, PixVerse, Google Veo, and a growing list of next-gen generative AI models that are redefining how video gets made. But with new models launching every week, it’s hard to know what’s worth your time—or how they actually fit into your workflow.
Trusted by 1M+ creators
When it comes to amazing videos, all you need is VEED
No credit card required
More than an AI dubbing API
The dubbing API is one endpoint on a platform built to take video from idea to post. Generate talking videos from a single image with Fabric 1.0, build on the latest frontier models in one workflow, then refine the output with subtitles, lip-sync, and clean audio. Add your brand kit so every version looks like your brand made it, not AI. Export post-ready video for YouTube, TikTok, Reels, and LinkedIn in every language your audience speaks in minutes.