Wireflow is now a Claude connector.

Set it up→

HeyGen Voice Clone

Copy agent promptDownload schemaOpen in a workflowCopy link

Clone an uploaded voice sample with HeyGen Voice 1 (instant clone) and save a private voice to your Wireflow account.

Audio / voiceFrom 15 creditsHeyGen

Input

6 fields

Result Idle

Your result will appear here.

Set your inputs, then open a workflow to create it.

Credit estimate uses the model defaults. Your workflow shows the final estimate for your inputs before you run.

Pairs well with

Sync

Sync Lipsync v3

Sync.so sync-3. high quality lip sync from video + audio

Video~80 credits at default settings
Kuaishou

Kling AI Avatar

Kling AI Avatar - Create talking head videos from images with audio

Video~92 credits at default settings
Model guide

Build with HeyGen Voice Clone.

Clone an uploaded voice sample with HeyGen Voice 1 (instant clone) and save a private voice to your Wireflow account.

Read the HeyGen Voice Clone docs

Best for

Clone an uploaded voice sample with HeyGen Voice 1 (instant clone) and save a private voice to your Wireflow account. Use the playground to set up a single step, then open a workflow when you want to connect more tools.

Inputs explained

Voice Sample (required)
Upload or record 1 to 3 minutes of clean speech from one speaker in an Import node, as MP3 or WAV. HeyGen uses the first 3 minutes. The sample must be uploaded to your Wireflow account. Type: audio.
Voice Name (optional)
Name shown in your saved private voice list (up to 64 characters). Type: text. Default: "Wireflow voice".
Language (optional)
Language spoken in the sample. Auto lets HeyGen detect it; set it if the clone fails its checks. Type: text. Options: auto, ar, be, bg, ca, cs, da, de, el, en, es, fa, fi, fr, he, hi, hr, hu, id, it, ja, ko, mk, ms, nl, pl, pt, ro, ru, sk, sl, sr, sv, ta, th, tl, tr, uk, vi, zh. Default: "auto".
Similarity (optional)
How closely the voice follows the recording. Max is what HeyGen recommends for sounding like the speaker. Type: text. Options: Medium, High, Extra high, Max (closest match). Default: "max".
Remove Background Noise (optional)
Clean the recording before cloning. Type: boolean. Default: true.
I own this voice or have permission to clone it (required)
Set the i own this voice or have permission to clone it used by this model. Type: boolean. Default: false.

Tips before you run

Start with the default settings and change one input at a time. Keep the result you like on your board so the next step can use it.

If you add a reference file, use a link the workflow can read. Check the inputs and credit estimate on the board before starting a run.

Working with this model

Clone and use a voice

  1. Add an Import node. Upload audio, or choose Record audio and record 1 to 3 minutes of clean speech from one speaker. MP3 or WAV; HeyGen uses the first 3 minutes.
  2. Connect the Import output to Voice Sample on a HeyGen Voice Clone node. Set Voice Name and check I own this voice or have permission to clone it.
  3. Wire Voice ID into the voice_id port of a HeyGen TTS node, and a script into its text port.
  4. Run the Voice Clone node explicitly. This costs 15 credits. Recording and uploading do not run the clone. The voice is usually ready in seconds.

The saved voice is private to your account. It shows up in the HeyGen TTS voice list and in GET /api/v1/voices?provider=heygen, so you can reuse it in other workflows without cloning again.

Settings

  • Similarity defaults to Max, which HeyGen recommends for sounding like the speaker.
  • Language is detected from the sample. If the clone fails HeyGen's checks, set it and run again.
  • Remove Background Noise is on by default.

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": "heygen", "name": "My narration", "audioUrl": "<completed upload URL>", "consentConfirmed": true }. Add "script": "..." (up to 750 characters) to also get a HeyGen TTS node wired to the clone, so one run clones the voice and speaks the script. Preparing the draft costs nothing. Run it with the returned nodeIds (REST) or targetNodeIds (MCP run_workflow), then poll the execution for voice_id.

Limits

  • Sample must be a completed MP3 or WAV upload owned by your Wireflow account, 25 MB max.
  • 5 HeyGen clones per account. Reuse a saved voice rather than cloning again. Delete one you no longer need with DELETE /api/v1/voices/<id> or MCP delete_voice; that deletes it at HeyGen and frees the place.
  • A clone HeyGen cannot finish is deleted and the credits are refunded.

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.

Common questions

How do I use HeyGen Voice Clone on Wireflow?

Set the inputs above and choose Open in a workflow. Sign in to save your board, then check its credit estimate before you run.

Can I use HeyGen Voice Clone through an API?

Yes. Save a workflow with this model, then call the Wireflow run API with its workflow ID. The API tab has examples you can copy.

What changes the credit price?

The price shown uses the model defaults. Your inputs and model settings can change the total. The workflow shows an estimate before you run.

Can I connect this to another model?

Yes. Open it in a workflow and connect its output to another node with a matching input type.