You can click on the link below to try it out directly. If the effect is good, you can deploy it locally<a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/1968314493635842049/?inviteCode=1cqzbf7a">https://www.runninghub.ai/post/1968314493635842049/?inviteCode=1cqzbf7a</a>Fan benefits,register to get 1000 points,daily login 100 points,play 4090!Experience the super power of 48G.This is a workflow for replicating human voices and emotions, which can generate emotional audio of single person speech or two person conversation. Better to use than previous models that generate stiff vocals, strongly recommended. The deployment difficulty of ComfyUI is relatively high. Firstly, the transformer version needs to be 4.51.0; Ensure the presence of the JSON5 module. Project page: <a target="_blank" rel="ugc" href="https://github.com/billwuhao/ComfyUI_IndexTTS">https://github.com/billwuhao/ComfyUI_IndexTTS</a> Model download link: <a target="_blank" rel="ugc" href="https://hf-mirror.com/nvidia/bigvgan_v2_22khz_80band_256x/tree/main">https://hf-mirror.com/nvidia/bigvgan_v2_22khz_80band_256x/tree/main</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/funasr/campplus/tree/main">https://hf-mirror.com/funasr/campplus/tree/main</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/IndexTeam/IndexTTS-2/tree/main">https://hf-mirror.com/IndexTeam/IndexTTS-2/tree/main</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/amphion/MaskGCT/tree/main/semantic_codec">https://hf-mirror.com/amphion/MaskGCT/tree/main/semantic_codec</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/facebook/w2v-bert-2.0/tree/main">https://hf-mirror.com/facebook/w2v-bert-2.0/tree/main</a> Model placement structure:- bigvgan_v2_22khz_80band_256x bigvgan_<a target="_blank" rel="ugc" href="http://generator.pt">generator.pt</a> config.json - campplus campplus_cn_common.bin - IndexTTS-2 │ .gitattributes │ bpe.model │ config.yaml │ <a target="_blank" rel="ugc" href="http://feat1.pt">feat1.pt</a> │ <a target="_blank" rel="ugc" href="http://feat2.pt">feat2.pt</a> │ gpt.pth │ <a target="_blank" rel="ugc" href="http://README.md">README.md</a> │ s2mel.pth │ wav2vec2bert_<a target="_blank" rel="ugc" href="http://stats.pt">stats.pt</a> │ └─ qwen0.6bemo4-merge added_tokens.json chat_template.jinja config.json generation_config.json merges.txt model.safetensors Modelfile special_tokens_map.json tokenizer.json tokenizer_config.json vocab.json - MaskGCT semantic_codec model.safetensors - w2v-bert-2.0 .gitattributes config.json conformer_<a target="_blank" rel="ugc" href="http://shaw.pt">shaw.pt</a> model.safetensors preprocessor_config.json <a target="_blank" rel="ugc" href="http://README.md">README.md</a>

IndexTTS2_ Vocal and Emotional Transfer _ Two person Dialogue+Single person Speaking Workflow

indextts2VocalAndEmotional_v10.zip

v1.0

You can click on the link below to try it out directly. If the effect is good, you can deploy it locally<a target="_blank" rel="ugc" href="https://www.runninghub.ai/post/1968294270253838337/?inviteCode=sdhs0trb">https://www.runninghub.ai/post/1968294270253838337/?inviteCode=sdhs0trb</a>Fan benefits,register to get 1000 points,daily login 100 points,play 4090!Experience the super power of 48G.<a target="_blank" rel="ugc" href="https://buymeacoffee.com/a592991299o">https://buymeacoffee.com/a592991299o</a>This is a workflow for replicating human voices and emotions, which can generate emotional audio of single person speech or two person conversation. Better to use than previous models that generate stiff vocals, strongly recommended. The deployment difficulty of ComfyUI is relatively high. Firstly, the transformer version needs to be 4.51.0; Ensure the presence of the JSON5 module. Project page: <a target="_blank" rel="ugc" href="https://github.com/billwuhao/ComfyUI_IndexTTS">https://github.com/billwuhao/ComfyUI_IndexTTS</a> Model download link: <a target="_blank" rel="ugc" href="https://hf-mirror.com/nvidia/bigvgan_v2_22khz_80band_256x/tree/main">https://hf-mirror.com/nvidia/bigvgan_v2_22khz_80band_256x/tree/main</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/funasr/campplus/tree/main">https://hf-mirror.com/funasr/campplus/tree/main</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/IndexTeam/IndexTTS-2/tree/main">https://hf-mirror.com/IndexTeam/IndexTTS-2/tree/main</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/amphion/MaskGCT/tree/main/semantic_codec">https://hf-mirror.com/amphion/MaskGCT/tree/main/semantic_codec</a> <a target="_blank" rel="ugc" href="https://hf-mirror.com/facebook/w2v-bert-2.0/tree/main">https://hf-mirror.com/facebook/w2v-bert-2.0/tree/main</a> Model placement structure:- bigvgan_v2_22khz_80band_256x bigvgan_<a target="_blank" rel="ugc" href="http://generator.pt">generator.pt</a> config.json - campplus campplus_cn_common.bin - IndexTTS-2 │ .gitattributes │ bpe.model │ config.yaml │ <a target="_blank" rel="ugc" href="http://feat1.pt">feat1.pt</a> │ <a target="_blank" rel="ugc" href="http://feat2.pt">feat2.pt</a> │ gpt.pth │ <a target="_blank" rel="ugc" href="http://README.md">README.md</a> │ s2mel.pth │ wav2vec2bert_<a target="_blank" rel="ugc" href="http://stats.pt">stats.pt</a> │ └─ qwen0.6bemo4-merge added_tokens.json chat_template.jinja config.json generation_config.json merges.txt model.safetensors Modelfile special_tokens_map.json tokenizer.json tokenizer_config.json vocab.json - MaskGCT semantic_codec model.safetensors - w2v-bert-2.0 .gitattributes config.json conformer_<a target="_blank" rel="ugc" href="http://shaw.pt">shaw.pt</a> model.safetensors preprocessor_config.json <a target="_blank" rel="ugc" href="http://README.md">README.md</a>

Files with SHA256: b4bc82e4795320fd4c2f85f1bb72a208aa36b44f0cb28f5c3b5a1e8760273d1b