<h1 id="ltxv-2.3-video-to-audio-comfyui-workflow">🎬 LTXV 2.3 Video-to-Audio — ComfyUI Workflow</h1>Add synced audio to your silent videos using LTXV 2.3's native joint audio-video generationTake any silent video and let LTXV 2.3 generate natural-sounding audio that actually matches what's happening on screen — footsteps, ambience, impacts, and more. Unlike tools that bolt on a separate audio model, LTXV 2.3 generates audio and video from within a single Diffusion Transformer model, so sync happens at the model level rather than in post.<hr /><h2 id="what-this-does">✨ What This Does</h2>This workflow uses LTXV 2.3's native joint audio-video generation — audio and video are produced together inside a single Diffusion Transformer (DiT) model, with sync happening at the model level. Feed it a silent MP4, describe the sound you want, and get back a video with synced audio baked in. No separate audio model, no manual alignment.<hr /><h2 id="how-to-use">🚀 How to Use</h2><ol><li>Load the workflow — drag the <code>.json</code> file into ComfyUI or use Load from the menu.</li><li>Input your video — connect your silent video file to the Load Video node. MP4 works best; keep it under 10 seconds to start.</li><li>Write your audio prompt — describe the sounds you want (e.g. <code>"footsteps on gravel, distant wind, birds chirping"</code>). Be specific — it responds well to descriptive prompts.</li><li>Set your seed — different seeds give noticeably different results, so worth exploring a few.</li><li>Run — hit Queue Prompt and grab a coffee. The output video with merged audio will appear in your <code>output/</code> folder.</li></ol><hr /><h2 id="where-this-fits-in-your-workflow">🔄 Where This Fits in Your Workflow</h2>For best results, run this after frame interpolation but before upscaling:<pre><code>Generate Video → Frame Interpolation → 🎧 Add Audio (here) → Upscale</code></pre>Why this order matters (Mostly speed of use):<ul><li>After interpolation — interpolation can subtly alter frame timing and motion cadence. Running audio generation on the interpolated video means the model is analyzing the final motion, giving you tighter sync.</li><li>Before upscaling — upscalers don't touch the audio track, so it doesn't matter where upscaling falls from an audio perspective. But keeping it last means you're not running a heavy upscale pass on a clip you might still tweak.</li></ul>💡 If you're using a temporal upscaler (like LTXV's own latent upscaler), treat it the same as interpolation — add audio after it.<hr /><h2></h2><h2 id="sex-sounds-loras-used-in-examples">🍆💦 Sex Sounds Loras used in examples</h2><ul><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2476698/ltx-23-deepthroat">https://civarchive.com/models/2476698/ltx-23-deepthroat</a></li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2514206/ltxv-23-audio-only-clapping-cheeks">https://civarchive.com/models/2514206/ltxv-23-audio-only-clapping-cheeks</a></li></ul><hr /><h2 id="example-inputs-and-outputs">🎧 Example Inputs &amp; Outputs</h2>Input VideoPromptResultPerson walking through forest<code>"footsteps on dry leaves, wind through trees, distant birdsong"</code>Footsteps land on every step, ambient nature bed underneathObject falling and hitting floor<code>"heavy thud, small objects scattering, room reverb"</code>Impact synced to hit frame, natural room echoWaves on a beach<code>"ocean waves crashing, gentle sea foam, seagulls"</code>Continuous wave sync matched to motion rhythm💡 Tip: The model pays attention to motion intensity. Fast movement + an energetic prompt = much better results than a mismatch between the two.<hr /><h2 id="known-limitations-and-tips">⚠️ Known Limitations &amp; Tips</h2>Limitations<ul><li>I</li><li>Works best on videos under 10 seconds — longer clips may drift out of sync toward the end.</li><li>Speech and singing are not reliably reproduced — this shines on environmental and ambient sound, not voice.</li></ul>Tips that actually help<ul><li>🎯 Be descriptive in your prompt — <code>"sharp metallic clang with reverb"</code> beats <code>"metal sound"</code> every time.</li><li>🔁 Run multiple seeds — audio generation has real variance; what sounds off on seed 42 might be perfect on seed 7.</li><li>🎚️ Check your input video FPS — the workflow assumes 24fps by default. If your video is a different frame rate, adjust the FPS node accordingly or sync will be off.</li></ul>

Files with SHA256: d6da584a690dd2bcbabccbfcf0e047ebdb7fb7769e64a55de727e9b9eab9e255