OmniVoice Workflows – Voice Design, Cloning, Multi‑Speaker, Digital Human & ASR

Click here to try first:

Workflow: OmniVoice Sound Design – Chinese Dialects – English Accents  

Experience URL: style="font-family:Calibri;font-size:10.5pt">  

Workflow: OmniVoice Multi-person Voice Cloning – Dialogue – Up to 10 People!  

Experience URL: style="font-family:Calibri;font-size:10.5pt">  

Workflow: OmniVoice Voice Cloning / Long Text Cloning – 600+ Languages Supported  

Experience URL: style="font-family:Calibri;font-size:10.5pt">  

Workflow: Speech-to-Text – Video Subtitle SRT Generation – Qwen3-ASR  

Experience URL: style="font-family:Calibri;font-size:10.5pt">  

Workflow: Auto-generate Digital Human V2 – OmniVoice Sound Design (Dialect Support!) – Infinite Talk Dynamic Digital Human  

Experience URL: style="font-family:Calibri;font-size:10.5pt">  

Workflow: Film & News Digital Human – Realistic LongCat Voice Cloning – High Dynamics Infinite Talk  

Experience URL: style="font-family:Calibri;font-size:10.5pt">  

Workflow: Extract Audio from Video – OmniVoice Single-person Voice Cloning  

Experience URL: style="font-family:Calibri;font-size:10.5pt"> 

Description (English):

A complete set of OmniVoice workflows for voice design, voice cloning, and video dubbing – all ready to run on Runninghub.

What’s included:

�� Voice Design – Control gender, age, pitch, style (Chinese dialects & English accents). Simple prompt stacking.

�� Single & Long‑Text Cloning – 600+ languages. High fidelity to the reference audio.

�� Multi‑Person Cloning – Up to 10 speakers with adjustable pause between dialogues.

�� Digital Human V2 – Auto‑generate talking avatar with Infinite Talk + voice design.

��️ Video Audio Extraction + Cloning – Perfect for fan editing / film re‑cutting.

�� ASR & Subtitles – Qwen3‑ASR for speech‑to‑text and SRT generation.

Why use these workflows:

✅ Extremely fast – 2 minutes of cloned audio in ~40 seconds

✅ Natural voice design with minimal prompts

✅ Open‑source, no closed‑platform dependency

✅ Plug‑and‑play nodes – some workflows need only 2 nodes!

Try them here:

style="font-family:Calibri;font-size:10.5pt">... (see links in the video or description)

All workflows are tested and explained in the attached video. Great for AI voice dubbing, digital humans, and multilingual content.

If you need a Chinese version for Civitai (some users post bilingual):