{
 "schema_version": 1,
 "generated": "2026-10-20",
 "repo": "Tencent-Hunyuan/AuK",
 "name": "AuK",
 "owner": "Tencent-Hunyuan",
 "slug": "tencent-hunyuan-auk",
 "github": "https://github.com/Tencent-Hunyuan/AuK",
 "what": "AuK is an open-source 1.5B speech model that generates and edits speech from natural-language instructions.",
 "why": "",
 "language": "Python",
 "requirements": [
  "Python 3.10 and uv or Conda",
  "A GPU with enough VRAM to run the model (CPU offload is CUDA only)",
  "Disk space and network access to download the AuK weights and the Qwen2.5-Omni-3B encoder from Hugging Face or ModelScope",
  "Source audio or a reference clip for tasks that need one"
 ],
 "audience_note": "Audio producers, localization teams, and developers who need to generate, clean up, or edit speech from a script or an existing recording.",
 "risk": "dual-use",
 "section": "earlier",
 "weekly_rank": null,
 "category": "Content",
 "url": "https://dedupedai.com/use-cases/tencent-hunyuan-auk/",
 "use_case_count": 5,
 "use_cases": [
  {
   "id": "tencent-hunyuan-auk--clone-voice-from-reference-clip",
   "title": "Generate speech in a reference speaker's voice",
   "best": true,
   "url": "https://dedupedai.com/use-cases/tencent-hunyuan-auk/clone-voice-from-reference-clip/",
   "json": "https://dedupedai.com/use-cases/u/tencent-hunyuan-auk/clone-voice-from-reference-clip.json"
  },
  {
   "id": "tencent-hunyuan-auk--create-speech-from-voice-description",
   "title": "Create speech from a voice description alone",
   "best": false,
   "url": "https://dedupedai.com/use-cases/tencent-hunyuan-auk/create-speech-from-voice-description/",
   "json": "https://dedupedai.com/use-cases/u/tencent-hunyuan-auk/create-speech-from-voice-description.json"
  },
  {
   "id": "tencent-hunyuan-auk--edit-words-in-existing-recording",
   "title": "Replace or remove words in an existing recording",
   "best": false,
   "url": "https://dedupedai.com/use-cases/tencent-hunyuan-auk/edit-words-in-existing-recording/",
   "json": "https://dedupedai.com/use-cases/u/tencent-hunyuan-auk/edit-words-in-existing-recording.json"
  },
  {
   "id": "tencent-hunyuan-auk--clean-noisy-speech-recording",
   "title": "Remove noise and reverb from a voice recording",
   "best": false,
   "url": "https://dedupedai.com/use-cases/tencent-hunyuan-auk/clean-noisy-speech-recording/",
   "json": "https://dedupedai.com/use-cases/u/tencent-hunyuan-auk/clean-noisy-speech-recording.json"
  },
  {
   "id": "tencent-hunyuan-auk--turn-free-form-request-into-auk-command",
   "title": "Turn a plain-language request into a ready-to-run command",
   "best": false,
   "url": "https://dedupedai.com/use-cases/tencent-hunyuan-auk/turn-free-form-request-into-auk-command/",
   "json": "https://dedupedai.com/use-cases/u/tencent-hunyuan-auk/turn-free-form-request-into-auk-command.json"
  }
 ],
 "disclaimer": "Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk."
}