<div data-youtube-video><iframe width="640" height="480" allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/9mA7BzsHRn8" start="0"></iframe></div>Click here to try online first : Workflow: Text-to-Speech – LongCat AudioDiT TTS (Auto Translation)Experience link: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2039728380941176834/?inviteCode=rh-v1401">https://www.runninghub.ai/post/2039728380941176834/?inviteCode=rh-v1401</a> Workflow: Single-Person Voice Cloning – LongCat-AudioDiT (Auto Translation)Experience link: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2039728236652924929/?inviteCode=rh-v1401">https://www.runninghub.ai/post/2039728236652924929/?inviteCode=rh-v1401</a> Workflow: Two-Person Voice Cloning – LongCat-AudioDiT – Dialogue – Script – ScreenplayExperience link: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2039728409407918081/?inviteCode=rh-v1401">https://www.runninghub.ai/post/2039728409407918081/?inviteCode=rh-v1401</a> Workflow: All-Purpose Image Pro – Text-to-Image – Single, Double, Triple, Quadruple Images – Image EditingExperience link: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2026244873988345857/?inviteCode=rh-v1401">https://www.runninghub.ai/post/2026244873988345857/?inviteCode=rh-v1401</a> Workflow: Lip-Sync Speaking &amp; Singing – LTX2.3 Image-to-Digital Human – Auto Expansion – Module Optimization – No SubtitlesExperience link: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2038618856104665090/?inviteCode=rh-v1401">https://www.runninghub.ai/post/2038618856104665090/?inviteCode=rh-v1401</a> Workflow: AA – Various Small Tools for Image, Audio, Video Processing (Continuously Updated)Experience link: <a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/2027021102093967362/?inviteCode=rh-v1401">https://www.runninghub.ai/post/2027021102093967362/?inviteCode=rh-v1401</a>    This set includes three ComfyUI workflows based on Meituan's open-source LongCat – a SOTA-level TTS model with high timbre fidelity and fast inference. Workflows included: Text-to-Speech – Convert any text to speech. Supports BF16/FP32. More steps = better quality. Single Voice Cloning – Upload a reference voice, write your target text, and generate cloned speech. Includes ASR (Qwen) for automatic transcription of the sample. Dual Voice Cloning – Generate a dialogue between two speakers. Format the prompt properly (speaker tags) for the model to recognize. Important notes: ⚠️ Numbers – Do NOT use Arabic numerals (e.g., 123). Always write numbers in their spoken Chinese form (e.g., "一百二十三"). Otherwise the output will be garbled. Voice loudness – The workflow automatically normalizes loudness to avoid pops/clipping. Keep the default reduction amount unless your source is extremely loud (red waveform in editors). Model precision – BF16 works well; FP32 requires ~20GB VRAM. Random seed – Controls some variation (cannot specify gender/tone directly). Recommended for: Film dubbing, AI-generated dialogue scenes, podcast-style dual-voice content. Combine with LTX 2.3 for image-to-digital human animation to create cinematic conversation scenes. For best results, use single cloning per fixed shot – dual cloning may cause unwanted frame transitions in LTX 2.3. Requirements: ComfyUI with custom nodes (ASR, LongCat, etc.) LongCat model files (see project page in comments) Timestamps (in video):Text-to-speech setup → Voice cloning → Dual dialogue → Integration with LTX 2.3 Enjoy making AI-powered film shorts! Feel free to ask questions below.

Files with SHA256: 081309189875edc3f5d1e457014c5e23873b27f1a12e4e71e53135108ebfa44a