Do I need an ElevenLabs API key for this workflow?

Yes. The ElevenLabs nodes call the ElevenLabs API. Enter your API key in the node or extension settings before running. If you see authentication errors (e.g., 401), re-check the key and your account permissions.

How do the performance tags work, and why might they seem to have no effect?

Eleven v4 treats your text as a performance script. Place tags like [whispers] or [excited] in square brackets immediately before or after the words you want to affect. If the effect seems subtle, move the tag closer to the specific phrase, simplify surrounding punctuation, and ensure the TTS node is using the Eleven v4 model.

What makes a good sample for Instant Voice Clone?

Use a clean, dry recording of a single speaker with minimal background noise and consistent mic distance. Avoid music or heavy processing. You can import a file with LoadAudio or capture a short, clear recording with RecordAudio. Only clone voices you have the legal right and consent to use.

How do I control the output file format and quality?

Use SaveAudioAdvanced to set the filename, location, and available audio parameters such as format and sample rate. If you plan to edit later, choose a higher-quality setting; for quick previews, use a smaller file format if offered.

Can I generate very long scripts?

Long scripts are possible but may be limited by your ElevenLabs plan and request timeouts. For reliability, split long content into sections in the Note/MarkdownNote, render them sequentially, and combine the results in your audio editor.

Eleven v4: Text to Speech - ComfyUI Workflow

This ComfyUI workflow turns written scripts into expressive speech using ElevenLabs’ Eleven v4 model. It’s designed around two clear paths: use a preset voice from your ElevenLabs library or instantly clone a voice from an audio sample. The core generation happens in the ElevenLabsTextToSpeech node, which reads your script (written in a Note/MarkdownNote) and applies performance directions you embed as inline tags like [whispers], [excited], [laughs], [sighs], [sarcastic], and [crying]. SaveAudioAdvanced then writes a single audio file to disk.

Technically, Option 1 (Use Preset Voice) routes a selection from ElevenLabsVoiceSelector into ElevenLabsTextToSpeech along with your script and the Eleven v4 model choice. Option 2 (Create a Voice Clone) feeds audio from LoadAudio or RecordAudio into ElevenLabsInstantVoiceClone, which returns a temporary voice you can target in the TTS node. Only one option group should be enabled at a time (select the group and press Ctrl-B to un-bypass it). Because Eleven v4 treats the prompt as a performance script, the workflow lets you direct tone and delivery directly in text while keeping the node graph compact and easy to iterate for narration, audiobooks, and character voiceovers.

API

Use this workflow from code

Every Comfy workflow is a JSON graph. The payload below is this workflow, exactly as ComfyUI runs it — fetch it from the URL, keep it in version control, or load it in ComfyUI and run it node by node.

bdb2c0ea519b.json

Fetching workflow JSON…

Run it from TypeScript or Python with the Comfy SDK. The same code targets Comfy Cloud or a ComfyUI you host yourself — only the base URL changes.

// Install (beta)
npm i @comfyorg/sdk

// Run this workflow (TypeScript)
import { Comfy } from "@comfyorg/sdk";

const client = new Comfy({ apiKey: "comfyui-..." });
const wf = await client.workflows.fromFile("workflow_api.json");
const job = await client.run(wf);
await job.getOutputs("<output-node-id>")[0].toFile("output.png");

The SDK takes a workflow in API format: open this workflow in ComfyUI and use File → Export Workflow (API).

Comfy Cloud API access requires a plan with an API key.

SDK docs Get an API key

FAQ

Frequently Asked Questions