EmbeddingGemma 2 Text 270M (LiteRT-LM)
litert-community · Kit
Turns text into vectors for search, clustering and question answering on phones and laptops. A 270M text-only EmbeddingGemma 2 build packaged for LiteRT-LM, co…
A Gradio app for making AI song covers with voice conversion models. Runs in your browser on Hugging Face, or on your own computer with Python 3.12.
AICoverGen is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on . Download it on this page, a zip of its files. Nothing in it runs by itself.
pip install -U huggingface_hub hf download r3gm/AICoverGen --repo-type space --local-dir AICoverGen cd AICoverGen
AICoverGen is a Gradio app for making AI covers of songs. Judging by its name and its folders for voice models, vocal models and song output, it swaps the voice in a song for a voice from a conversion model.
The Space names voice conversion models, including a Hubert base model and several voice packs. The source gives no step-by-step guide beyond that.
It suits hobbyist musicians and curious listeners who want to hear a song in another voice, and developers who want to read how a voice conversion demo is put together.
| Industry | Who uses it | How they use it | Example |
|---|---|---|---|
| Music | Hobby musicians | Try a voice model on a song they own | Hearing a demo track in a different voice |
| Content creation | Video makers | Make a cover for a personal project | Preparing a clip with a changed vocal |
| AI development | Developers | Read app.py and the src folder | Learning how a voice conversion app is organised |
| Education | Students | Open the page and see how voice conversion works | Comparing the sound of two voice models |
Skip it if you plan to copy a real person's voice without their permission, since that is not a use this page is meant for.
The app runs in these places.
| Use case | Who | What they get back |
|---|---|---|
| Make a cover online | Hobby musicians | A converted song from the browser page |
| Try different voice models | Creators | Covers to compare by ear |
| Study the app | Developers | A repository with src, rvc_models and mdxnet_models folders |
Online you only need a browser. A local copy needs these.
pip install -U huggingface_hub hf download r3gm/AICoverGen --repo-type space --local-dir AICoverGen cd AICoverGen pip install gradio==6.20.0 pip install -r requirements.txt python app.py
Open the Space's page, or run the command below in your copy and open the page the app serves. Then choose a song and a voice model and run it.
python app.py
You open the Space, pick a song and one of the voice models, and run it. The app produces a cover in the new voice, and the repository keeps finished tracks in a song_output folder.
If you are new, open the Space's page and try a short clip first. A short test shows you how a voice model sounds before you spend time on a full track.
If you know the field, the repository holds rvc_models and mdxnet_models folders, a src folder and an images folder, in 37 files. It names the RVC voice conversion project and a Hubert base model. Online it runs on zero-a10g hardware with Gradio 6.20.0.
Hugging Face lists the Space with a Gradio tag. Check that you may use both a song and a voice before you share a cover.
A Gradio app for making AI song covers with voice conversion models. Runs in your browser on Hugging Face, or on your own computer with Python 3.12.
Made by r3gm on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.
What it is: AICoverGen is a Gradio app for making AI covers of songs. Judging by its name and its folders for voice models, vocal models and song output, it swaps the voice in a song for a voice from a conversion model.
The Space names voice conversion models, including a Hubert base model and several voice packs. The source gives no step-by-step guide beyond that.
Who it suits: It suits hobbyist musicians and curious listeners who want to hear a song in another voice, and developers who want to read how a voice conversion demo is put together.
Industry | Who uses it | How they use it | Example
Music | Hobby musicians | Try a voice model on a song they own | Hearing a demo track in a different voice
Content creation | Video makers | Make a cover for a personal project | Preparing a clip with a changed vocal
AI development | Developers | Read app.py and the src folder | Learning how a voice conversion app is organised
Education | Students | Open the page and see how voice conversion works | Comparing the sound of two voice models
Skip it if you plan to copy a real person's voice without their permission, since that is not a use this page is meant for.
Where to use it: The app runs in these places.
Use case | Who | What they get back
Make a cover online | Hobby musicians | A converted song from the browser page
Try different voice models | Creators | Covers to compare by ear
Study the app | Developers | A repository with src, rvc_models and mdxnet_models folders
How to set it up: Online you only need a browser. A local copy needs these.
pip install -U huggingface_hub
hf download r3gm/AICoverGen --repo-type space --local-dir AICoverGen
cd AICoverGen
pip install gradio==6.20.0
pip install -r requirements.txt
python app.py
How to use it: Open the Space's page, or run the command below in your copy and open the page the app serves. Then choose a song and a voice model and run it.
python app.py
Example: You open the Space, pick a song and one of the voice models, and run it. The app produces a cover in the new voice, and the repository keeps finished tracks in a song_output folder.
For newcomers and experts: If you are new, open the Space's page and try a short clip first. A short test shows you how a voice model sounds before you spend time on a full track.
If you know the field, the repository holds rvc_models and mdxnet_models folders, a src folder and an images folder, in 37 files. It names the RVC voice conversion project and a Hubert base model. Online it runs on zero-a10g hardware with Gradio 6.20.0.
Open the Space page or run app.py
Choose a song and a voice model
The app converts the vocals
The cover shows on the same page
Good to know: Hugging Face lists the Space with a Gradio tag. Check that you may use both a song and a voice before you share a cover.
Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.
README.md 4 KB
Listed Hugging Face Spaces in the same category that share the most tags with this one.
| Product | Likes | Built with | License | Last change |
|---|---|---|---|---|
| AICoverGen This page | 542 | gradio | mit | |
| FLUX.1 [Schnell]Shares gradio | 5,162 | gradio | mit | |
| MusicGenShares gradio | 5,116 | gradio | cc-by-nc-4.0 | |
| Kokoro TTSShares gradio | 3,556 | gradio | apache-2.0 | |
| Background RemovalShares gradio | 2,988 | gradio | mit | |
| Omni Image EditorShares gradio | 2,922 | gradio | mit |
litert-community · Kit
Turns text into vectors for search, clustering and question answering on phones and laptops. A 270M text-only EmbeddingGemma 2 build packaged for LiteRT-LM, co…
google · Kit
Turns images and text into matching embeddings, with spatial patch features, for zero-shot image classification. Google's Base variant of TIPSv2, for vision re…
Elevatormusic · Kit
Runs DeepSeek V4.1 Flash on two NVIDIA DGX Spark computers at about twice the decode and prefill speed of a standard vLLM setup. A recipe card with no weights,…
black-forest-labs · Kit
Generates pictures from text prompts with the FLUX.1 schnell model from black-forest-labs, in a browser demo built with Gradio. It suits designers and creators…
ACE-Step · Kit
Generates music from text with a 4B diffusion decoder, 50 steps and guidance control, aiming for higher audio quality than the base. For creators with a GPU of…
op7418 · Skill
Skill that makes single-file HTML slide decks, slide illustrations and platform covers in two visual styles, with a presenter mode for rehearsal. For speakers…