Keep your branding consistent using familiar voices from key speakers
Record or upload a short voice sample to get custom cloned voices. Using ElevenLabs API, your AI voices are realistic and nearly identical to the original speaker's voice. Save your own high-quality custom voices with direct access to a video editing platform so you can add voice overs directly to video.
Multilingual support for voice translation in over 20 languages
Capture key cultural nuances across languages for a global reach. Translate your AI-cloned voice to over 20 languages, including Spanish, Arabic, Chinese, and more. Make second and third languages sound like your first with AI voice dubbing.
Instant voice cloning with custom voice samples as short as 10 seconds
If you're racing against a deadline, upload a short voice sample and get a cloned voice—all under two minutes. If you don't have an audio file on hand, record your own voice in the editor to clone with AI. Save your own custom voices and reuse them directly to later projects.
“As a social media agency owner, there's a variety of video needs that my clients have. From adding subtitles to resizing videos for various platforms, Kapwing makes it possible for us to create incredible content that consistently exceeds client expectations.”
CEO of Moxie Nashville
Fine tune your audio with AI-powered features and a full creative suite
Experiment with over 50 unique voices to capture the exact tone you want
Save yourself hours of time listening to voice samples and coordinating recording sessions. With a built-in AI voice library, you can swap out different natural-sounding voices straight to your video, until you find the perfect one.
Get free access to a full library of sound effects and background music
Ever spent an hour finding the perfect song only to discover it was off limits due to copyright? Grab your favorite royalty-free songs and sound effects from Kapwing’s built-in music library with thousands of tracks perfect for background music. Directly add music to videos and save your work all in one place.
Improve audio quality drastically with a background noise remover
Perfect when narrating videos, audiobooks, or video games, instantly clean up your audio by removing background noise. In just a few clicks, make your voice sound clearer with the built-in audio enhancer.
"Kapwing is incredibly intuitive. Many of our marketers were able to get on the platform and use it right away with little to no instruction. No need for downloads or installations—it just works."
Studio Production Manager at Formlabs
How to use the AI voice cloner
- Open Text to Speech
In the editor, click the “Audio” tab on the right-hand sidebar to open Text to Speech.
- Upload a voice sample
Scroll through the different voice options and select "Add new voice" to upload a short voice sample to clone.
- Clone voice and edit
Name the custom voice you want to save and apply voice cloning AI (also referred to as voice dubbing). Apply directly to a video project or export and download an MP3 file of your audio.
Frequently Asked Questions
What languages do you support?
Kapwing supports (and is still adding) over 20 languages while preserving the original speaker's accent: English (US, UK, Australia), Arabic (Multi-region), Chinese (Mandarin), Czech, Danish, Dutch, Filipino (Tagalog), French, German, Greek, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Norwegian, Polish, Portuguese, Spanish (Spain, Mexico), and Swedish.
How can I get the best quality out of voice cloning?
Although Kapwing is smart enough to clone a voice from as short as a 10-second voice sample, the more audio material you feed this AI voice cloning tool, the more realistic your cloned voice will get. This includes capturing key speech patterns in intonation and cadences to give you an identical sounding custom voice.
What's different about Kapwing?
Kapwing is free to use for teams of any size. We also offer paid plans with additional features, storage, and support.