Create a reusable voice profile with Voice Clone

Create a voice profile from connected sample audio, provider, name, description, and language, then reuse that profile in voice workflows.

Where: Flowgen → Add → Audio → Voice Clone

Before you start

• Use only a voice you own or have explicit permission to clone.

Key ideas

• Sample in, profile out: Connect sample audio on the left; the node emits a Voice Profile that Voice Swap or compatible speech generation can consume.
• Provider metadata: Choose the provider and supply a clear name, description, and language so the resulting profile remains identifiable.
• Preview before reuse: The card can preview both the input sample and the created voice result when available.
• Voice Clone card: VoiceCloneNode uses the generic shared-card path. Create a reusable voice profile from an authorized connected audio sample.
• Properties sidebar: renderAudioNodes.tsx
• Opened surfaces: Sample/profile audio preview

Steps

1. Connect an authorized, clean sample recording.
2. Choose the provider and enter the profile name, description, and language.
3. Create the profile and preview the result beside the original sample.
4. Connect the Voice Profile output to Voice Swap or another compatible voice input.

Voice Clone controls and presets

• Add path: Flowgen → Add → Sound → Voice Clone.
• Card: VoiceCloneNode.
• Properties: renderAudioNodes.tsx.
• Controls: Provider; name; description; language; sample/import.
• Opened surfaces: Sample/profile audio preview.

Tips

• Use a dry recording with one speaker, little room noise, and representative pronunciation.
• Name the profile for the speaker and intended use, not a generic version number.

Limitations and important notes

• Provider requirements and supported languages can differ.
• A voice profile is not proof of consent or permission.

Related guides

• Replace a recording voice with Voice Swap
• Text-to-Speech (AI Voice)
• Synchronize speech with the Lip Sync node