ElevenLabs Voice Clone
Clone an uploaded voice sample with ElevenLabs Instant Voice Cloning and save a private voice to your Wireflow account. Outputs a voice_id you can wire into ElevenLabs TTS (Custom Voice).
Try ElevenLabs Voice Clone in the playground
ElevenLabs Voice Clone
Badge: Direct
Node type: audio:elevenlabs_voice_clone
Category: audio
Description
ElevenLabs Voice Clone uses ElevenLabs Instant Voice Cloning to save a private voice to your Wireflow account from 30 to 120 seconds of clean speech from one speaker: upload or record the sample in an Import node, connect it to Voice Sample, set Voice Name, check I own this voice or have permission to clone it, and run the Voice Clone node explicitly. Recording and uploading do not run the clone. Wire the Voice ID it outputs into the voice_id port of an ElevenLabs TTS (Custom Voice) node, with a script in its text port. The clone costs 50 credits and is a one-time cost; speaking with it afterwards is the ElevenLabs TTS (Custom Voice) price. You get 5 ElevenLabs clones per account, so reuse a saved voice rather than cloning again.
Clone and use a voice
- Add an Import node. Upload audio, or choose Record audio and record 30-120 seconds of clean speech from one speaker.
- Connect the Import output to Voice Sample on an ElevenLabs Voice Clone node. Set Voice Name and check I own this voice or have permission to clone it.
- Wire Voice ID into the
voice_idport of an ElevenLabs TTS (Custom Voice) node, and a script into itstextport. - Run the Voice Clone node explicitly. This costs 50 credits. Recording and uploading do not run the clone.
The saved voice is private to your account. It shows up at the top of the ElevenLabs TTS (Custom Voice) voice list and in GET /api/v1/voices?provider=elevenlabs, so you can reuse it in other workflows without cloning again.
API and agents
Upload the recording (POST /api/v1/media/upload, or POST /api/v1/media/upload-url then /complete for files up to 25 MB). Then call POST /api/v1/voices/clone-workflow or MCP prepare_voice_clone with { "provider": "elevenlabs", "name": "My narration", "audioUrl": "<completed upload URL>", "consentConfirmed": true }. Add "script": "..." to also get a TTS node wired to the clone, so one run clones the voice and speaks the script. Preparing the draft costs nothing. Over MCP it needs the workflows:write scope, which is opt-in; a default connection can run workflows but cannot create the draft. Run it with the returned nodeIds (REST) or targetNodeIds (MCP run_workflow), then poll the execution for voice_id.
- Cost: ~50 credits per generation
- A clone is a one-time cost. Speaking with it afterwards is the ElevenLabs TTS (Custom Voice) price.
Canvas ports
These appear as port handles on the left side of the node.
| ID | Label | Details |
|---|---|---|
audio_url |
Voice Sample | AUDIO (required) — Upload or record 30-120 seconds of clean speech from one speaker in an Import node. The sample must be uploaded to your Wireflow account. |
Sidebar config
These render as form fields in the right-side config panel when the node is selected.
| ID | Label | Details |
|---|---|---|
title |
Voice Name | TEXT — Name shown in your saved private voice list. |
consent_confirmed |
I own this voice or have permission to clone it | BOOLEAN (required) |
Outputs
| ID | Label | Type |
|---|---|---|
voice_id |
Voice ID | TEXT |
Limits
- Sample must be a completed WAV, MP3 or M4A upload owned by your Wireflow account, 25 MB max. External URLs must be uploaded to Wireflow first.
- 5 ElevenLabs clones per account. Reuse a saved voice rather than cloning again. Delete one you no longer need with
DELETE /api/v1/voices/<id>or MCPdelete_voice; that deletes it at ElevenLabs and frees the place. - When the shared ElevenLabs account is near its voice limit, the run is refused before any credits move. Fish Voice Clone is the fallback.
Notes
- Clean beats long. Background music, reverb, and two people talking all end up in the clone.
- One run makes one voice. Re-running the same run returns the voice it already made; a new run makes a new voice.
- Only clone voices you have the right to clone. Consent is recorded with the voice.