The 'Chatter Box: Multi-Speaker Conversation with Cloned Voices' workflow is designed to create realistic multi-speaker audio conversations using voice cloning technology. By leveraging the Chatter Box model, this workflow allows users to upload short voice samples for each speaker and input a dialog script. The workflow then generates an audio file where each speaker's part is voiced using the cloned voices. This is achieved using a series of nodes: **FL_ChatterboxDialogTTS** for text-to-speech conversion with cloned voices, **LoadAudio** for uploading voice samples, **AudioCrop** for trimming audio clips if necessary, and **SaveAudioMP3** for exporting the final audio file. Additionally, the **MarkdownNote** node can be used to annotate the workflow with instructions or notes. This workflow is particularly useful for creating personalized audio content, such as podcasts, audiobooks, or virtual assistants, where distinct and recognizable voices enhance the listener's experience.
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.
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 "Chatter Box: Multi-Speaker Conversation with Cloned Voices" (TypeScript)
import { Comfy } from "@comfyorg/sdk";
const client = new Comfy({ apiKey: "comfyui-..." });
// This workflow, exported in API format (see note below)
const wf = await client.workflows.fromFile("audio-chatterbox_tts_dialog_api.json");
const job = await client.run(wf);
await job.getOutputs("5")[0].toFile("output.png"); // SaveAudioMP3The 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.
FAQ
