DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to generate speech in a reference speaker's voice with AuK

Turn a script into spoken audio that keeps the voice of a short reference recording using zero-shot TTS.

  • Top pick
  • Content
  • Intermediate
  • 1 hour
  • From the README
  • Any agent

Authorization notice. AuK is dual-use. Only use it on software, sites and systems you own or have explicit permission to test.

Voice cloning. The output imitates the reference speaker, so use only voices you have permission to clone.

Who it is forA content creator or narrator who has a short clip of a voice they are allowed to use and needs a new line read in that voice.

The problemRecording every new script line again is slow, and the voice must match the earlier recording.

The outcomeA WAV file with the target text spoken in the reference voice at the chosen length.

What you need first

  • 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

Steps

  1. git clone https://github.com/Tencent-Hunyuan/AuK
  2. cd AuK
  3. uv venv --python 3.10
  4. source .venv/bin/activate
  5. uv pip install -e .
  6. hf download tencent/AuK --local-dir ./ckpts/AuK
  7. hf download Qwen/Qwen2.5-Omni-3B --local-dir ./ckpts/Qwen2.5-Omni-3B (inferred, check the README)
  8. auk-infer --audio <reference.wav> --instruction "Say the following with the same voice: '<target text>'" --output <out.wav> --gen_seconds 6.0 (inferred, check the README)

Prompt for your agent

Using the Tencent-Hunyuan/AuK repo, set up the environment and download the AuK and Qwen2.5-Omni-3B weights, then run auk-infer with <reference.wav> and the target text <target text> to write <out.wav>. Verify that <out.wav> exists and plays back at about the requested length, and report the path only if the speaker permission for <reference.wav> is confirmed.

Caveat. The README gives a duration hint through --gen_seconds, so the output length may need adjusting for your script.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page