General Introduction
Funmaru Thousand Voices is a multilingual AI voice synthesis platform that provides realistic and natural voice generation solutions. Users can easily convert text content into professional-grade audio and support the creation of exclusive AI voices (voice clones) from zero samples to meet personalized needs. The platform also provides a video translation function to help users realize the rapid conversion of multilingual content.
Function List
- multilingual synthesis: Supports text-to-speech in multiple languages to meet different language needs.
- video translation: Provides multilingual translation and subtitle generation for video content.
- sound cloning: Quickly generate similar sounds by providing audio samples.
- Mouth synchronization:The video follows the post-translation language synchronized with the character's mouth. (to be opened)
- Personalized voice: Freely adjust the age, mood, accent and other parameters of the voice.
- Professional-grade audio generation: The generated audio is rich in emotion and rhythm and is suitable for a wide range of scenarios.
Using Help
multilingual synthesis
A sentence-second replica of your timbre and generate multilingual speech with emotions. Voice fast cloning by open source modeling MaskGCT Support.
Procedure for use
- Click the "Add" button;
- In the Upload Audio column, upload 15s of audio and select the "Original Language" for that audio;
- Enter the text you wish to synthesize and select the "target language" for this text (this can be the same as the original language).
- Finally, click on the "Synthesize" button and wait a moment to listen to it!
video translation
Not only does it replicate the original character's timbre to speak other languages, but it also supports matching the lip-sync to a new language!
Procedure for use
- Click to upload video
- Select "Original Language" and "Translation Language" and click "Start Translation".
- After waiting for the successful translation, click on the work to enter the editing page, you can preview the translated video, support for download, share!
- New effects can be synthesized again by modifying the original text and translation, as well as matching subtitles and lip-synching (not yet available in the public beta free version)
