Skip to content
WorkflowListedExternal
Open source

Wan 2.1/Multitalk/Chatterbox - Poor Man's Veo 3 — v1.0

This lets you bring an image, a couple lines of dialog, and a short voice sample and get speaking character videos out of Wan 2.1. Thanks to Kijai for adding multitalk capability to the WanWrapper series of nodes.

Sourcecivitai.com/models/1876104
TaskText to videoFamilyWanVersionRelease 2123489 — wan-multitalk-chatterbox.jsonEstimated VRAMNot yet characterizedBgrade

Runtime profile

Access
External workflow
Status
Listed
Version
wan-multitalk-chatterbox.json
Source
Civitai
Updated
Oct 18, 2026

Source description

This lets you bring an image, a couple lines of dialog, and a short voice sample and get speaking character videos out of Wan 2.1. Thanks to Kijai for adding multitalk capability to the WanWrapper series of nodes.

Helpful links:

Github of the chatterbox node implementation I'm using:

https://github.com/diodiogod/ComfyUI_ChatterBox_SRT_Voice

Lots of demo voices you can download here:

https://resemble-ai.github.io/chatterbox_demopage/

Kijai's nodes:

https://github.com/kijai/ComfyUI-WanVideoWrapper

What you need

Model files
0.2 GiB known subtotal

Remaining hardware or download-size estimates are not available yet.

Requirements

Models

7

Node packs

8

AI-generated commentary

AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.

Purpose

  • Use this workflow to turn an image, a couple lines of dialogue, and a short voice sample into speaking-character videos with Wan 2.1.

Inputs and outputs

  • The workflow lists LoadImage, LoadAudio, Text Multiline, WanVideoImageToVideoMultiTalk, WanVideoDecode, and VHS_VideoCombine nodes.

Setup

  • The description links to a Chatterbox voice-node implementation, downloadable demo voices, and Kijai’s WanVideoWrapper nodes.

Dependencies

  • The named node packs are audio-separation-nodes-comfyui, chatterbox_srt_voice, comfyui-kjnodes, comfyui-ollama, comfyui-videohelpersuite, ComfyUI-WanVideoWrapper, rgthree-comfy, and was-node-suite-comfyui.

  • The model list names CLIP-ViT-H-14-laion2B-s32B-b79K.safetensors, TencentGameMate/chinese-wav2vec2-base, umt5-xxl-enc-bf16.safetensors, Wan2_1_VAE_bf16.safetensors, Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors, Wan21_I2V_14B_lightx2v_cfg_step_distill_lora_rank64.safetensors, and  .

Configuration

  • The listed base model is Wan Video 14B t2v, and this release is v1.0.

Cautions

  • Check that the named node packs and model files are available in your ComfyUI setup before using the workflow.

    Suggestion · not verified

  • No license is listed; check the source page for usage terms.

    Suggestion · not verified

Does this need to be edited?

Sign in to send an edit request.

Sources

1 source
CivitaiPrimaryVersion 2123489
civitai.com/models/1876104

Verified Oct 18

Source excerpts

3 excerpts
NoteOct 18civitai.com/models/1876104

Source context: 565 downloads · Type Workflows · Base model Wan Video 14B t2v

NoteAug 7civitai.com/models/1876104

Source context: 517 downloads · Type Workflows · Base model Wan Video 14B t2v

NoteJul 19civitai.com/models/1876104

Source context: 502 downloads · Type Workflows · Base model Wan Video 14B t2v