Instant, not a training job
Upload samples, get an identity. There is no training run to configure and no dataset to prepare, which makes cloning a step in a workflow rather than a project of its own.
Voice Clone turns recordings of a speaker into a reusable Voice ID using ElevenLabs Instant Voice Cloning. Upload one or more clean samples, run the node, and you get an identity you can generate new lines with for as long as you need it.
The Voice ID drops straight into Sound Creation for narration or Dialogue Creation for two-speaker scenes, so pickups, corrections, and localised versions all come back in the same voice as the original.
Dubbing, localisation, narration pickups, corrections, and recurring character voices
Localisation, media, and brand teams keeping one speaker consistent across a series
Turn recordings into a reusable voice identity, then generate new lines in it indefinitely.
Upload samples, get an identity. There is no training run to configure and no dataset to prepare, which makes cloning a step in a workflow rather than a project of its own.
The Voice ID works across sessions and across nodes. Clone the speaker once and every pickup, correction, and new line for the rest of the project comes back in the same voice.
Generate translated or rewritten lines in the original speaker's voice. With Eleven v3 the accent character carries across languages, so the same person is recognisable in every market version.
Enable Remove Background Noise for imperfect source recordings, and leave it off when the audio is already clean. One toggle instead of a separate cleanup pass before the clone.
The Voice ID drops into Sound Creation for narration and Dialogue Creation for two-speaker scenes, on the same canvas as your video and image nodes. No exporting audio to a separate tool and back.
Voice Clone fits wherever new lines have to sound like a specific person: localisation, pickups, corrections, and long-running series.
Upload clean samples, run the node, and reuse the Voice ID downstream.
Attach one or more clean recordings of the target speaker to the Voice Audio input. Several short representative clips beat one long noisy file, and every sample should contain only the one speaker.
Turn on Remove Background Noise only if the source has audible noise. Leave it off for clean studio recordings. Run the node and copy the Voice ID from the output.
Paste the Voice ID into the custom voice field of Sound Creation or Dialogue Creation and generate as many lines as you need. The identity is reusable indefinitely, so the same voice carries across a whole project.
One subscription across 30+ AI models, with no per-tool credit balances or separate signups. Credit cost per run is shown live in the node before you start it.
500 weekly credits to test the node and hear the output quality. No credit card required.
45,000 monthly credits with cheaper per-credit pricing, commercial rights, and full downloads.
90,000 monthly credits, up to 10 seats, shared workspace, centralized billing, and priority support.
210,000 monthly credits, API and integration support, unlimited seats, and dedicated management.
Full specs for Voice Clone in Phygital+.
How Voice Clone fits alongside the other audio nodes in Phygital+.
Clone a voice once, then reuse it across every audio node on the canvas.
Paste the Voice ID into Sound Creation and generate unlimited narration in the cloned voice.
Clone two speakers and assign one Voice ID to each side of a two-person scene.
Translate or rewrite the script in a text node, then generate the new lines in the original speaker's voice.
Generate the visuals in a video node and lay the cloned voice track underneath.
Everything you need to know about Voice Clone in Phygital+.
Voice Clone builds a voice identity from audio samples using ElevenLabs Instant Voice Cloning. It does not produce speech itself. It returns a Voice ID, which you then paste into Sound Creation or Dialogue Creation to generate new lines in that voice.
Clean recordings where the target speaker is isolated and clearly intelligible. Several short representative clips work better than one long noisy file. Avoid music, overlapping speakers, heavy room echo, and loud background noise, and keep every sample to a single speaker: mixed voices make the resulting Voice ID unreliable.
Turn on Remove Background Noise when the source recording has audible noise. Leave it off for clean studio recordings, since a clean file usually needs less processing and the extra pass can only take something away.
Run the node, copy the Voice ID from the output, and paste it into the custom voice field of Sound Creation for narration or Dialogue Creation for a two-speaker scene. The Voice ID is reusable indefinitely, so you clone once and generate as many lines as you need.
Yes, that is one of the main reasons to use it. Clone the speaker once, then generate translated or rewritten lines in Sound Creation. With Eleven v3 a cloned voice keeps its accent character across languages, so the speaker stays recognisable in each localised version.
There is no text prompt on this node. The audio you supply is the reference, and output quality depends entirely on how clear and consistent those samples are. Everything about the result is decided by the source material.
Get explicit permission from the speaker before cloning their voice, and check the model card and applicable law for your use case. Cloning a real person's voice without consent is not something to work out after the fact.
Usage is credit-based and included in every plan, from Free up to Enterprise. The credit cost per run is shown in the node before you start it, so there is no separate ElevenLabs subscription to manage.
Outputs created on any paid plan come with commercial-use rights, provided you have permission for the voice you cloned.
Browse the full catalog of 30+ AI models available in Phygital+.
Join 100+ teams using Phygital+ – every model in one workspace
Try Phygital+ free