Ranked #1 in Speech Arena
AI voice dubbing in 44 languages
Hear AI dubbing voices in Spanish, French, and Japanese
Spanish
IriaSpain
Durante la siesta en Sevilla, la Giralda proyectaba una sombra. Mateo juró ver una silueta misteriosa que cruzaba lentamente detrás de las columnas.During siesta in Seville, the Giralda cast a shadow. Mateo swore he saw a mysterious silhouette slowly crossing behind the columns.
French
ÉtienneCanada
La tempête faisait rage sur la Grande Allée à Québec, où la poudrerie cachait le Château Frontenac.The storm was raging on Grande Allée in Québec City, where the blowing snow hid the Château Frontenac.
Japanese
NaokiJapan
アマゾンの密林で、ピップという小さなアマガエルは、一筋の光に導かれながら、一生に一度の大冒険に出かけようとしていた。In the Amazon rainforest, a small tree frog named Pip was embarking on a lifetime adventure, guided by a single ray of sunlight.
Join the teams making the switch to Cartesia
How to dub a video with AI voices
Four steps take a translated script to a finished language version. Cartesia makes the voice track; your video editor fits it to the picture.
Split the translated script
Break the translation at each scene and speaker change, so you can regenerate one line without redoing the rest.
Pick a voice for each speaker
Choose from 500+ voices in the library, or clone the original speaker with their permission and add an accent for each language.
Generate the lines
Create each line in the Playground or through the API. Set the emotion and speed, and add pronunciations for names and brand terms.
Drop the audio into your edit
Place each WAV or MP3 clip on your timeline and mix it with the music and effects.
Dubbed lines that sound native in each market
Set an accent or a pronunciation once and every line follows. Adjust emotion and speed line by line.
Native accents
Add an accent to a voice so it sounds native in Mexican Spanish or Brazilian Portuguese. Each accented version is saved as a new voice.
Explore voice localizationNames said right
Add a name or brand term to a pronunciation dictionary once, and the voice says it your way in every line and retake.
Delivery that fits the scene
Choose from 60+ emotions and set the speed and volume of each line, so a calm aside and an angry warning don't sound alike.
Keep the original speaker's voice in every language version
Clone the speaker in their own language from 10 seconds of audio, then add accents so the same voice speaks natively in each language you dub into.
Explore AI voice cloningEvery language from one API
Generate speech in 44 languages, including Spanish with a Mexican or Castilian accent, Hindi, Japanese, and Arabic.
American English, 3 voices
American English
Explore more voice tools
AI dubbing FAQs
What is AI dubbing?
AI dubbing replaces the speech in a video with generated speech, usually in another language. A dub has three parts: a translated script, a voice track, and an edit that fits the track to the picture. Cartesia generates the voice track from your script, in 40+ languages.
Can AI dub my voice?
Yes. With Cartesia, record 10 seconds of audio in your own language to make an Instant Voice Clone, then add voice accents so the clone speaks every language you dub into with a native accent.
Is AI dubbing free?
Cartesia has a Free plan with 20,000 credits a month, enough to generate and compare test scenes in the Playground. Paid plans add more credits and a commercial-use license; see pricing.
Is AI dubbing legal?
It depends on rights. You need rights to the video and script, consent from anyone whose voice you clone, and a commercial-use license, which Cartesia's paid plans include. Read the terms of service and acceptable use policy before you publish.
Is there an AI dubbing API?
Yes. Cartesia's text-to-speech API turns each translated line into WAV, MP3, or raw audio, so a localization pipeline can generate the voice track for every language version in code.
Which languages can I dub into?
Cartesia generates speech in 40+ languages, including Spanish, French, German, Japanese, Portuguese, Hindi, and Chinese, with regional accents for English, Spanish, French, Portuguese, and more. Hear them on the language pages, and see the model guide for the full list.
How do I make the dub fit the scene?
Generate one scene at a time and listen against the picture. If a line runs long, shorten the translation, add a pause, or raise the speed with the voice controls.
How do I dub a video with several speakers?
Give each speaker their own voice and generate their lines as separate clips. Name each clip by speaker and scene, so you can drop a revised line into the right spot on your timeline.
What is the difference between dubbing and voiceover?
A voiceover adds narration over the picture. Dubbing replaces what people on screen say, usually in another language, and has to match their timing. Cartesia generates the speech for both; for narration, see AI voiceover.
Get started today
Talk to an expert.
Connect with a member of our team and learn how Cartesia can help you build world-class voice experiences.
Start building.
Access our models via API and bring a voice agent into production in minutes.