Chatter Box: Multilingual Text-to-Speech with Voice Cloning
Upload a short voice sample and input your text prompt. Select a target language to generate spoken audio in multiple languages using the cloned reference voice.
例を試す
このワークフローについて
The 'Chatter Box: Multilingual Text-to-Speech with Voice Cloning' workflow is designed to transform text into spoken audio across multiple languages using a cloned voice from a short audio sample. This workflow leverages the Chatter Box model, which is adept at voice cloning and multilingual text-to-speech synthesis.
By using the **FL_ChatterboxMultilingualTTS** node, users can input a text prompt and select a target language for audio generation. The workflow begins with the **LoadAudio** node, where a short voice sample is uploaded to define the voice characteristics for cloning. The generated audio is then saved using the **SaveAudioMP3** node, allowing for easy access and sharing.
This workflow is particularly useful for creating personalized multilingual audio content, making it a valuable tool for content creators, educators, and businesses aiming to reach a global audience.
よくある質問
You should upload a clear and short audio clip in a common format like WAV or MP3 to ensure the best voice cloning results.
Currently, the workflow supports generating audio in one language at a time. You can repeat the process for different languages.
A short clip of around 10-30 seconds is usually sufficient for effective voice cloning.
While there is no strict limit, shorter prompts tend to generate faster and more accurate results. Consider breaking longer texts into smaller sections.