{
  "schemaVersion": "1.0",
  "updates": [],
  "companyNews": [],
  "id": "b889",
  "language": "en",
  "name": "F5-TTS",
  "originalName": "F5-TTS",
  "library": "tools",
  "category": "Audio & music",
  "categoryKey": "音频音乐",
  "categoryKeys": [
    "音频音乐"
  ],
  "categories": [
    "Audio & music"
  ],
  "entryPoints": [],
  "summary": "Generate speech from reference audio, its transcript and target text, with chunked inference, multi-voice sequences and fine-tuning.",
  "introduction": "F5-TTS conditions new speech on reference audio and its transcript. Command-line and Gradio workflows support chunked synthesis, multiple styles and speakers, plus training and fine-tuning. Omitting the reference transcript invokes an additional recognition model. Code uses MIT, while official pretrained weights use non-commercial CC-BY-NC terms; code, weights and training data have distinct usage conditions.",
  "capabilities": [],
  "company": {
    "name": "F5-TTS project",
    "originalName": "F5-TTS project"
  },
  "officialUrl": "https://github.com/SWivid/F5-TTS",
  "profileUpdatedOn": "2026-10-22",
  "sources": [
    {
      "kind": "product",
      "url": "https://github.com/SWivid/F5-TTS"
    },
    {
      "kind": "documentation",
      "url": "https://huggingface.co/SWivid/F5-TTS"
    }
  ],
  "news": [],
  "links": {
    "interactive": "products/f5-tts--b889.html",
    "reading": "read/en/products/f5-tts--b889.html",
    "markdown": "read/en/products/f5-tts--b889.md",
    "json": "read/en/products/f5-tts--b889.json"
  }
}