<p><strong>One-click create multi-speaker lip-sync videos from portraits and voices!</strong></p><p><strong>Who it's for:</strong> creators who want this pipeline in ComfyUI without assembling nodes from scratch. <strong>Not for:</strong> one-click results with zero tuning — you still choose inputs, prompts, and settings.</p><h3 id="open-preloaded-workflow-on-runcomfy">Open preloaded workflow on RunComfy</h3><p><a target="_blank" rel="ugc" href="https://www.runcomfy.com/comfyui-workflows/comfyui-multitalk-workflow-multi-speaker-lip-synced-video-generator?utm_source=civitai&amp;utm_medium=referral">Open preloaded workflow on RunComfy (browser)</a></p><p><strong>Why RunComfy first</strong><br />- <strong>Fewer missing-node surprises</strong> — run the graph in a managed environment before you mirror it locally.<br />- <strong>Quick GPU tryout</strong> — useful if your local VRAM or install time is the bottleneck.<br />- <strong>Matches the published JSON</strong> — the zip follows the same runnable workflow you can open on RunComfy.</p><p><strong>When downloading for local ComfyUI makes sense</strong> — you want full control over models on disk, batch scripting, or offline runs.</p><p><strong>How to use (local ComfyUI)</strong><br />1. Load inputs (images/video/audio) in the marked loader nodes.<br />2. Set prompts, resolution, and seeds; start with a short test run.<br />3. Export from the Save / Write nodes shown in the graph.</p><p><strong>Expectations</strong> — First run may pull <strong>large weights</strong>; cloud runs may require a <strong>free RunComfy account</strong>.</p><hr /><h3 id="overview">Overview</h3><p>This workflow generates lip-synced videos from portraits and audio, supporting both single and multi-speaker outputs with detailed facial motion and speech alignment.</p><p><strong>Important nodes:</strong></p><h2 id="key-nodes-in-comfyui-multitalk-workflow">Key nodes in ComfyUI MultiTalk workflow</h2><h3 id="multitalkwav2vecembeds-(79162)"><code>MultiTalkWav2VecEmbeds</code> (#79/#162)</h3><p>Converts one or more dialogue tracks into <strong>MultiTalk</strong> conversation embeddings. Start with one audio input for single-person or two for multi-person; add masks when you need per-face routing. Adjust only what matters: number of frames to match your planned clip length, and whether to provide <code>ref_target_masks</code> for precise speaker-to-face alignment.</p><h3 id="audioseparation-(88160161)"><code>AudioSeparation</code> (#88/#160/#161)</h3><p>Optional cleanup for noisy inputs. Route your noisy clip into this node and forward the <code>Vocals</code> output. Use it when field recordings include background music or chatter; skip it if you already have clean voice tracks.</p><h3 id="indexttsnode-(163164)"><code>IndexTTSNode</code> (#163/#164)</h3><p>Turns <code>Speaker 1 - Text</code> and <code>Speaker 2 - Text</code> into dialogue audio. Provide a short <code>reference_audio</code> to clone tone and pacing, then supply text lines. Keep sentences brief and natural for best lip timing in <strong>MultiTalk</strong>.</p><h3 id="wanvideotextencodesingle-(18)"><code>WanVideoTextEncodeSingle</code> (#18)</h3><p>Encodes your scene prompt for Wan 2.1. Favor simple, concrete descriptions of place, lighting, and style. Avoid long lists; one or two sentences are enough for the sampler to l</p><hr /><h3 id="notes">Notes</h3><p><strong>ComfyUI Multitalk Workflow | Multi-Speaker Lip-Synced Video Generator</strong> — see <a target="_blank" rel="ugc" href="https://www.runcomfy.com/comfyui-workflows/comfyui-multitalk-workflow-multi-speaker-lip-synced-video-generator?utm_source=civitai&amp;utm_medium=referral">RunComfy page</a> for the latest node requirements.</p>

Files with SHA256: de34ba8a7453a963d8927fa179092b50382fee8275af633def992cabf8f2e0a0