ワークフローに戻る

Chatter Box: Multi-Speaker Conversation with Cloned Voices

Upload voice samples and enter a multi-speaker dialog script. Generate a conversation audio file with cloned voices for each speaker.

ワークフローをダウンロードCloudで試す

Input

One line per turn, each starting with SPEAKER A: or SPEAKER B:.

5–10 seconds of one person speaking clearly.

  • 0:00 / 0:00

5–10 seconds of a second person speaking clearly.

  • 0:00 / 0:00

Emotional intensity of the delivery; 0.5 is neutral.

Default: 0.5

Advanced settings

How closely the delivery follows the voice samples' pacing.

Default: 0.5

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

End of the part of speaker B's sample to use (m:ss).

Default: 0:20

Start of the part of speaker B's sample to use (m:ss).

Default: 0:00

Higher values vary the delivery more.

Default: 0.8

Run

Output
Example
00:00

例を試す

このワークフローについて

The 'Chatter Box: Multi-Speaker Conversation with Cloned Voices' workflow is designed to create realistic multi-speaker audio conversations using voice cloning technology. By leveraging the Chatter Box model, this workflow allows users to upload short voice samples for each speaker and input a dialog script.

The workflow then generates an audio file where each speaker's part is voiced using the cloned voices. This is achieved using a series of nodes: **FL_ChatterboxDialogTTS** for text-to-speech conversion with cloned voices, **LoadAudio** for uploading voice samples, **AudioCrop** for trimming audio clips if necessary, and **SaveAudioMP3** for exporting the final audio file. Additionally, the **MarkdownNote** node can be used to annotate the workflow with instructions or notes.

This workflow is particularly useful for creating personalized audio content, such as podcasts, audiobooks, or virtual assistants, where distinct and recognizable voices enhance the listener's experience.

よくある質問