Kokoro Female Voices is a collection of audio LoRAs trained on Kokoro TTS voices.Currently, 3 voices are available: Nicole, Heart, BellaUsage<ul><li>Recommended strength: 0.5–0.7.</li><li>Higher strengths may still work, but they can cut out other sounds in the video and may cause lip-sync issues at high values.</li><li>Works with t2v (text-to-video), i2v (image-to-video), and ref2v (reference-to-video).</li><li>Each LoRA includes 3 example videos demonstrating these usages.</li><li>ComfyUI workflows are embedded in the videos—drag and drop them into ComfyUI to load them.</li><li>The example workflows use the default ComfyUI workflows plus the Comfy Kitchen node.</li><li>Settings used: 28 steps, res_multistep sampler, simple scheduler.</li></ul>Turbo / Refinement<ul><li>Lightly tested with Turbo; it works, but I recommend the ComfyUI-H3-AudioRefine node to improve results.</li></ul>Use Cases<ul><li>Consistent voices between scenes</li><li>Same voice across generations</li><li>A predictable voice for a character you want</li></ul>Credits / License Original repo used for training the voices: <a target="_blank" rel="ugc" href="https://github.com/nazdridoy/kokoro-tts">https://github.com/nazdridoy/kokoro-tts</a> <a target="_blank" rel="ugc" href="https://huggingface.co/hexgrad/Kokoro-82M">https://huggingface.co/hexgrad/Kokoro-82M</a> apache-2.0 License. Credit to the authors for this great tool.

Files with SHA256: 9f40f29413553e47e817b33a3196992bfad947094ea0efdad89ac723157be580