The 'Chatter Box: Multilingual Text-to-Speech with Voice Cloning' workflow is designed to transform text into spoken audio across multiple languages using a cloned voice from a short audio sample. This workflow leverages the Chatter Box model, which is adept at voice cloning and multilingual text-to-speech synthesis. By using the **FL_ChatterboxMultilingualTTS** node, users can input a text prompt and select a target language for audio generation. The workflow begins with the **LoadAudio** node, where a short voice sample is uploaded to define the voice characteristics for cloning. The generated audio is then saved using the **SaveAudioMP3** node, allowing for easy access and sharing. This workflow is particularly useful for creating personalized multilingual audio content, making it a valuable tool for content creators, educators, and businesses aiming to reach a global audience.
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: Multilingual Text-to-Speech with Voice Cloning" (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_multilingual_api.json");
const job = await client.run(wf);
await job.getOutputs("3")[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
