ワークフローに戻る

Chatter Box: Voice Cloning Audio Conversion

Upload an audio clip and a short voice reference to generate a converted audio output that clones the target voice while preserving the original timing and performance.

ワークフローをダウンロードCloudで試す

Input

A recording of the words you want; they are re-spoken in the target voice.

  • 0:00 / 0:00

About 10 seconds of one person speaking clearly; the result uses this voice.

  • 0:00 / 0:00
Advanced settings

Where to stop in the speech recording (m:ss).

Default: 0:27

Leave empty for a new result each run. Enter a number to repeat one.

Where to start in the speech recording (m:ss).

Default: 0:00

Run

Output
Example
00:00

例を試す

このワークフローについて

The 'Chatter Box: Voice Cloning Audio Conversion' workflow is designed to transform an audio clip into a different voice while maintaining the original timing and performance characteristics. This is achieved using the Chatter Box model, which specializes in voice cloning. The workflow begins with the 'LoadAudio' node, which imports the original audio clip you wish to convert. A short reference clip of the target voice is then processed using the 'FL_ChatterboxVC' node, which performs the voice conversion.

This node is crucial as it analyzes the target voice's characteristics and applies them to the original audio, ensuring that the output retains the original's timing and emotional nuances.

The workflow also includes the 'AudioCrop' node, which allows users to trim the audio to the desired length, ensuring only the relevant sections are processed. Finally, the 'SaveAudioMP3' node exports the converted audio in MP3 format, making it easy to share and use across various platforms. The inclusion of 'MarkdownNote' nodes helps document the process and provide guidance within the workflow. This setup is particularly useful for applications in dubbing, content creation, and personalized voiceovers, where maintaining the original performance's integrity is crucial.

よくある質問