[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-8b48f7ce":3,"seo:featured-workflow:8b48f7ce-4f09-11f1-9bc6-00163e2b0d79:fr":86,"workflow-related-asset-8b48f7ce-8b48f7ce-4f09-11f1-9bc6-00163e2b0d79":87},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":14,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":16,"tags":23,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":30,"asset_kind":31,"target_tools":32,"install_mode":36,"entrypoint":20,"risk_profile":37,"dependencies":39,"verification":45,"agent_metadata":48,"agent_fit":61,"trust":73,"provenance":82,"created_at":84,"updated_at":85},3660,"8b48f7ce-4f09-11f1-9bc6-00163e2b0d79","asset-8b48f7ce","GPT-SoVITS — Few-Shot Voice Cloning and Text-to-Speech","An open-source TTS system that can clone any voice from just one minute of audio data, combining GPT-style language modeling with VITS synthesis for natural speech generation.","8a911193-3180-11f1-9bc6-00163e2b0d79","AI Open Source","https:\u002F\u002Ftokrepo.com\u002Fapple-touch-icon.png",0,"",2,"en",[17],{"id":18,"step_order":19,"title":20,"description":13,"prompt_template":21,"variables":13,"depends_on":22,"expected_output":13},4234,1,"GPT-SoVITS Overview","# GPT-SoVITS — Few-Shot Voice Cloning and Text-to-Speech\n\n## Quick Use\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FRVC-Boss\u002FGPT-SoVITS.git\ncd GPT-SoVITS\npip install -r requirements.txt\npython webui.py\n# Open http:\u002F\u002Flocalhost:9874\n```\n\n## Introduction\nGPT-SoVITS is an open-source text-to-speech system that achieves voice cloning from as little as one minute of reference audio. It combines GPT-based language modeling for prosody with VITS (Variational Inference with adversarial learning for end-to-end TTS) for high-quality waveform synthesis.\n\n## What GPT-SoVITS Does\n- Clones a speaker's voice from 1-10 minutes of reference audio recordings\n- Generates natural-sounding speech in the cloned voice from text input\n- Supports cross-lingual voice cloning across Chinese, English, and Japanese\n- Provides a web UI for training, inference, and audio management\n- Includes tools for dataset preparation, annotation, and audio preprocessing\n\n## Architecture Overview\nGPT-SoVITS uses a two-stage pipeline. First, a GPT-based model predicts semantic tokens from text, capturing prosody and rhythm. Then a VITS-based model converts these tokens into a high-fidelity waveform matching the target speaker's voice characteristics. Speaker embedding is extracted from reference audio using a pretrained encoder, enabling few-shot adaptation.\n\n## Self-Hosting & Configuration\n- Requires Python 3.9+ with PyTorch and CUDA for GPU-accelerated training and inference\n- Pretrained base models are downloaded automatically on first run\n- Training a voice clone takes 30-60 minutes on a consumer GPU with 1 minute of audio\n- The web UI runs locally with no external API dependencies\n- Supports CPU-only inference at reduced speed for machines without GPUs\n\n## Key Features\n- One-minute voice cloning produces recognizable speaker identity and style\n- Cross-lingual synthesis supports Chinese, English, and Japanese text\n- Built-in dataset tools handle audio slicing, denoising, and automatic transcription\n- Fine-tuning from pretrained models converges quickly even on consumer hardware\n- Batch inference mode for generating large volumes of audio efficiently\n\n## Comparison with Similar Tools\n- **Bark** — generates speech with music and effects; GPT-SoVITS specializes in voice cloning fidelity\n- **Coqui TTS** — broader TTS toolkit; GPT-SoVITS achieves better few-shot cloning quality\n- **Fish Speech** — multilingual TTS; GPT-SoVITS offers a more mature training pipeline\n- **F5-TTS** — flow-matching approach; GPT-SoVITS uses GPT + VITS with established community support\n- **Kokoro** — lightweight TTS; GPT-SoVITS provides deeper voice cloning from minimal data\n\n## FAQ\n**Q: How much audio data is needed to clone a voice?**\nA: As little as 1 minute for basic cloning, though 5-10 minutes yields better results.\n\n**Q: Can it run on CPU only?**\nA: Yes, inference works on CPU but is significantly slower. Training requires a CUDA GPU.\n\n**Q: Is the output suitable for production use?**\nA: Quality is high for many use cases. Evaluate on your specific requirements.\n\n**Q: What audio formats are supported?**\nA: WAV is the primary format. MP3 and other formats are converted automatically during preprocessing.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002FRVC-Boss\u002FGPT-SoVITS","0",[24],{"id":25,"name":26,"slug":27,"icon":28},12,"Configs","config","⚙️",false,"5573cbd4107f4efe9bd79af170910ab17b5c2edcc483693c01a833fda23a200d","skill",[33,34,35],"claude_code","codex","gemini_cli","single",{"executes_code":29,"modifies_global_config":29,"requires_secrets":38,"uses_absolute_paths":29,"network_access":29},[],{"npm":40,"pip":41,"brew":43,"system":44},[],[42],"requirements.txt",[],[],{"commands":46,"expected_files":47},[],[20],{"asset_kind":31,"target_tools":49,"install_mode":36,"entrypoint":20,"risk_profile":50,"dependencies":52,"content_hash":30,"verification":57,"inferred":60},[33,34,35],{"executes_code":29,"modifies_global_config":29,"requires_secrets":51,"uses_absolute_paths":29,"network_access":29},[],{"npm":53,"pip":54,"brew":55,"system":56},[],[42],[],[],{"commands":58,"expected_files":59},[],[20],true,{"target":34,"score":62,"status":63,"policy":64,"why":65,"asset_kind":31,"install_mode":36},98,"native","allow",[66,67,68,69,70,71,72],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":74,"verified_publisher":29,"asset_signed_hash":30,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":76,"review_status":77,"signals":78},"established","hash_only",[],"unreviewed",[79,80,81],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":83,"content_hash":30,"visibility":19,"created_at":84,"updated_at":85},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-8b48f7ce","2026-05-14 04:23:03","2026-05-14 05:49:05",null,[88,140,194,241],{"id":89,"uuid":90,"slug":91,"title":92,"description":93,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":94,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":95,"tags":96,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":98,"asset_kind":31,"target_tools":99,"install_mode":36,"entrypoint":100,"risk_profile":101,"dependencies":103,"verification":108,"agent_metadata":111,"agent_fit":123,"trust":125,"provenance":128,"created_at":130,"updated_at":131,"__relatedScore":132,"__relatedReasons":133,"__sharedTags":138},2511,"f07fee9a-45df-11f1-9bc6-00163e2b0d79","asset-f07fee9a","GPT-NeoX — Open-Source Large Language Model Training Library","A GPU-optimized library by EleutherAI for training large-scale autoregressive language models. GPT-NeoX powered the training of GPT-NeoX-20B and Pythia, providing the open-source community with tools for billion-parameter model training.",92,[],[97],{"id":25,"name":26,"slug":27,"icon":28},"4480e03ed6f0fdc0567c6e7e2b22bb3fa2f85d933d3e13f190dc95c13dff7289",[33,34,35],"GPT-NeoX Overview",{"executes_code":29,"modifies_global_config":29,"requires_secrets":102,"uses_absolute_paths":29,"network_access":29},[],{"npm":104,"pip":105,"brew":106,"system":107},[],[],[],[],{"commands":109,"expected_files":110},[],[100],{"asset_kind":31,"target_tools":112,"install_mode":36,"entrypoint":100,"risk_profile":113,"dependencies":115,"content_hash":98,"verification":120},[33,34,35],{"executes_code":29,"modifies_global_config":29,"requires_secrets":114,"uses_absolute_paths":29,"network_access":29},[],{"npm":116,"pip":117,"brew":118,"system":119},[],[],[],[],{"commands":121,"expected_files":122},[],[100],{"target":34,"score":62,"status":63,"policy":64,"why":124,"asset_kind":31,"install_mode":36},[66,67,68,69,70,71,72],{"author_trust_level":74,"verified_publisher":29,"asset_signed_hash":98,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":126,"review_status":77,"signals":127},[],[79,80,81],{"owner_uuid":9,"owner_name":10,"source_url":129,"content_hash":98,"visibility":19,"created_at":130,"updated_at":131},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-f07fee9a","2026-05-02 12:32:34","2026-05-14 04:49:59",91.9527244228309,[134,135,136,137],"topic-match","same-kind","same-target","same-author",[27,139],"configs",{"id":141,"uuid":142,"slug":143,"title":144,"description":145,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":146,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":147,"tags":148,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":150,"asset_kind":31,"target_tools":151,"install_mode":36,"entrypoint":152,"risk_profile":153,"dependencies":155,"verification":160,"agent_metadata":163,"agent_fit":175,"trust":182,"provenance":187,"created_at":189,"updated_at":190,"__relatedScore":191,"__relatedReasons":192,"__sharedTags":193},1041,"d3b64571-35cb-11f1-9bc6-00163e2b0d79","zoxide-smarter-cd-command-learns-your-habits-d3b64571","zoxide — A Smarter cd Command That Learns Your Habits","zoxide is a smarter cd command written in Rust. It tracks directories you visit and lets you jump to any of them with just a few keystrokes. Inspired by z and autojump. Works with bash, zsh, fish, PowerShell, nushell, and more.",105,[],[149],{"id":25,"name":26,"slug":27,"icon":28},"13b4327219e3bf09b65e9b88e820d25b8faaf260fc04c0fa2e3e1cf8e3024ddc",[33,34,35],"SKILL.md",{"executes_code":29,"modifies_global_config":29,"requires_secrets":154,"uses_absolute_paths":29,"network_access":60},[],{"npm":156,"pip":157,"brew":158,"system":159},[],[],[],[],{"commands":161,"expected_files":162},[],[13],{"asset_kind":31,"target_tools":164,"install_mode":36,"entrypoint":152,"risk_profile":165,"dependencies":167,"content_hash":150,"verification":172},[33,34,35],{"executes_code":29,"modifies_global_config":29,"requires_secrets":166,"uses_absolute_paths":29,"network_access":60},[],{"npm":168,"pip":169,"brew":170,"system":171},[],[],[],[],{"commands":173,"expected_files":174},[],[13],{"target":34,"score":176,"status":177,"policy":178,"why":179,"asset_kind":31,"install_mode":36},64,"needs_confirmation","confirm",[66,67,68,180,181,72],"policy confirm","risk_profile.network_access is true",{"author_trust_level":74,"verified_publisher":29,"asset_signed_hash":150,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":183,"review_status":77,"signals":185},[184],"network_access",[186,79,80],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":188,"content_hash":150,"visibility":19,"created_at":189,"updated_at":190},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fzoxide-smarter-cd-command-learns-your-habits-d3b64571","2026-04-12 01:28:17","2026-05-13 17:01:33",78.03795879789716,[134,135,136,137],[27,139],{"id":195,"uuid":196,"slug":197,"title":198,"description":199,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":13,"fork_count":12,"vote_count":12,"view_count":200,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":201,"tags":202,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":204,"asset_kind":31,"target_tools":205,"install_mode":36,"entrypoint":206,"risk_profile":207,"dependencies":209,"verification":214,"agent_metadata":217,"agent_fit":229,"trust":231,"provenance":234,"created_at":236,"updated_at":237,"__relatedScore":238,"__relatedReasons":239,"__sharedTags":240},2305,"eb65b8c4-431c-11f1-9bc6-00163e2b0d79","d2-declarative-diagram-scripting-language-eb65b8c4","D2 — Declarative Diagram Scripting Language","A modern diagram scripting language that turns text into diagrams, offering a readable syntax for architecture, flow, and sequence diagrams rendered from code.",96,[],[203],{"id":25,"name":26,"slug":27,"icon":28},"2851a6609ce0c7a696ee46060bf63bd3fd30c9595d0d9ee4c3f763779c0ea314",[33,34,35],"D2 Overview",{"executes_code":29,"modifies_global_config":29,"requires_secrets":208,"uses_absolute_paths":29,"network_access":60},[],{"npm":210,"pip":211,"brew":212,"system":213},[],[],[],[],{"commands":215,"expected_files":216},[],[206],{"asset_kind":31,"target_tools":218,"install_mode":36,"entrypoint":206,"risk_profile":219,"dependencies":221,"content_hash":204,"verification":226},[33,34,35],{"executes_code":29,"modifies_global_config":29,"requires_secrets":220,"uses_absolute_paths":29,"network_access":60},[],{"npm":222,"pip":223,"brew":224,"system":225},[],[],[],[],{"commands":227,"expected_files":228},[],[206],{"target":34,"score":176,"status":177,"policy":178,"why":230,"asset_kind":31,"install_mode":36},[66,67,68,180,181,72],{"author_trust_level":74,"verified_publisher":29,"asset_signed_hash":204,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":232,"review_status":77,"signals":233},[184],[79,80],{"owner_uuid":9,"owner_name":10,"source_url":235,"content_hash":204,"visibility":19,"created_at":236,"updated_at":237},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fd2-declarative-diagram-scripting-language-eb65b8c4","2026-04-29 00:11:31","2026-05-13 18:57:48",74.98015760139937,[134,135,136,137],[27,139],{"id":242,"uuid":243,"slug":244,"title":245,"description":246,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":247,"time_saved":12,"model_used":248,"fork_count":12,"vote_count":12,"view_count":249,"parent_id":12,"parent_uuid":13,"lang_type":15,"steps":250,"tags":251,"has_voted":29,"visibility":19,"share_token":13,"is_featured":12,"content_hash":253,"asset_kind":31,"target_tools":254,"install_mode":36,"entrypoint":245,"risk_profile":257,"dependencies":259,"verification":264,"agent_metadata":267,"agent_fit":279,"trust":281,"provenance":284,"created_at":286,"updated_at":287,"__relatedScore":288,"__relatedReasons":289,"__sharedTags":290},262,"04367306-be4a-4f46-854d-dd2b4d0d429e","chroma-open-source-vector-database-ai-04367306","Chroma — Open-Source Vector Database for AI","Chroma is the open-source vector database and data infrastructure for AI applications. 27.1K+ GitHub stars. Simple 4-function API for embedding, storing, and querying documents. Supports Python, JavaS",500,"Claude Code",182,[],[252],{"id":25,"name":26,"slug":27,"icon":28},"00605e1a63ad3ac2a280050b36e245642efe82b5532b00967d9f612e49e70ed4",[33,34,255,35,256],"cursor","windsurf",{"executes_code":29,"modifies_global_config":29,"requires_secrets":258,"uses_absolute_paths":29,"network_access":29},[],{"npm":260,"pip":261,"brew":262,"system":263},[],[],[],[],{"commands":265,"expected_files":266},[],[245],{"asset_kind":31,"target_tools":268,"install_mode":36,"entrypoint":245,"risk_profile":269,"dependencies":271,"content_hash":253,"verification":276},[33,34,255,35,256],{"executes_code":29,"modifies_global_config":29,"requires_secrets":270,"uses_absolute_paths":29,"network_access":29},[],{"npm":272,"pip":273,"brew":274,"system":275},[],[],[],[],{"commands":277,"expected_files":278},[],[245],{"target":34,"score":62,"status":63,"policy":64,"why":280,"asset_kind":31,"install_mode":36},[66,67,68,69,70,71,72],{"author_trust_level":74,"verified_publisher":29,"asset_signed_hash":253,"signature_status":75,"install_count":12,"report_count":12,"dangerous_capability_badges":282,"review_status":77,"signals":283},[],[186,79,80,81],{"owner_uuid":9,"owner_name":10,"source_url":285,"content_hash":253,"visibility":19,"created_at":286,"updated_at":287},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fchroma-open-source-vector-database-ai-04367306","2026-03-31 20:19:12","2026-05-14 02:04:45",72.39367663459565,[135,136,137],[27,139]]