For Text Layers
Text-to-Speech
Converts text layers written in any of 18+ languages.
Input
Text layer or tap the AI button and then tap Text-to-Speech
Output
New spoken audio clip on the Timeline
Generates a fresh audio track from text.
AI Audio
Inside the AI button are two tools to make fully AI narrative audio tracks. Use Text-to-Speech to turn text into spoken audio in 19 languages: Korean, English, German, Japanese, Spanish, Portuguese, Arabic, Hindi, Thai, Vietnamese, and more. Or use AI Voice to transform the timbre, intonation, and tone of any existing music or voice clip using community voice profiles from the Asset Store. Both are free, both open from the Media Wheel.
What it does
Text-to-Speech and AI Voice solve different problems. Text-to-Speech converts text layers into brand-new spoken audio tracks, in your chosen language and voice. AI Voice takes an existing audio clip — music or voiceover — and changes it using a downloadable voice profile from the Asset Store. AI Voice adjusts the timbre, intonation, and tone while preserving the timing. Access Text-to-Speech when you select a text layer and AI Voice when you select an Audio Track. Both are free.
For Text Layers
Converts text layers written in any of 18+ languages.
Input
Text layer or tap the AI button and then tap Text-to-Speech
Output
New spoken audio clip on the Timeline
Generates a fresh audio track from text.
For Audio Layers
Re-voice any audio track with pre-made or community-created AI Voice from the Asset Store.
Input
Existing music or voice audio track + Asset Store AI Voice
Output
Muted original audio track and a re-voiced audio track from the chosen profile
AI Voices can be downloaded from the Asset Store, where user-made AI Voice files are provided for free. Timing of the original clip is preserved; timbre, intonation, and tone are changed.
18+ languages supported
Core
Korean · English · German · Japanese
Europe
Russian · French (France) · Portuguese (Portugal) · Spanish (Spain)
Americas
Portuguese (Brazil) · Spanish (Mexico)
MENA
Arabic (Jordan) · Arabic (Tunisia) · Persian (Iran) · Turkish
India
Hindi · Gujarati
Southeast Asia
Indonesian · Thai · Vietnamese
How to use
Access Text-to-Speech by tapping a text layer. Access AI Voice by tapping an audio layer.
Tap Text-to-Speech in the Tool Panel.
Some languages have more than one option. Choose the persona you like and tap Convert.
Preview the result, then insert as a new audio clip on the timeline.
Tap a music track or audio narration on the Timeline you want to re-voice.
Tap the AI Voice button in the Tool Panel.
Browse the Asset Store AI Voice category to download different AI Voice assets. The audio track's timing is preserved; only timbre, intonation, and tone change.
TipYou can upload your own voice to the Asset Store and share it with editors around the world. Log in on kinemaster.com to get started.
Use cases
From global multi-language channels to signature creator voices and community collaboration.
CASE 01
Re-export the same video in Spanish, Portuguese, Arabic, Hindi, Indonesian, and more — generate a new TTS narration for each language without re-recording.
CASE 02
Upload your voice once to the Asset Studio, then apply your own AI Voice to Text-to-Speech narrations or rough voiceover takes. Your signature tone on every video without recording every line.
CASE 03
Use another creator's published AI Voice to build collab-style content, parody, or character-driven storytelling without live recording sessions needed.
CASE 04
Apply AI Voice to a vocal music clip to swap timbre or accent while keeping the underlying performance — useful for stylistic remixes within personal projects.
FAQ
Quick answers about the functionality, supported languages, voice profile sources, uploads, supported clip types, and pricing.
Text-to-Speech turns text layers into a new audio clip and is available in 18+ languages. AI Voice takes an existing music or voice track and re-voices it with a community-made voice profile while preserving timing. Text-to-Speech and AI Voice are complimentary but have different purposes.
TTS supports 18+ locales: Korean, English, German, Japanese, Russian, Portuguese (Brazil/Portugal), Spanish (Spain/Mexico), French, Arabic (Jordan/Tunisia), Persian, Turkish, Hindi, Gujarati, Indonesian, Thai, and Vietnamese.
AI Voice profiles are created by KineMaster editors and are available to download from the Asset Store. Anyone can download and use AI Voices.
Yes. You can upload your voice using the Asset Studio, accessible when you log in to the kinemaster.com website.
AI Voice can be used with both music clips and narrative (spoken voice) audio tracks. The audio track's timing is preserved while timbre, intonation, and tone change.
Yes. Both tools are free. Text-to-Speech generation is free across all supported locales, and AI Voice profile downloads from the Asset Store are free.
Related features
Combine Text-to-Speech and AI Voice with related KineMaster audio tools to take your voice production further.
Record live narration, then apply AI Voice to re-voice it with a community profile
After generating Text-to-Speech or applying AI Voice, enhance it further with EQ, Reverb, or Pitch adjustments
Clean up source audio tracks before AI Voice conversion for better results
Pair AI Voice narration with auto-generated captions in matching languages
Download KineMaster free on iOS and Android.