






I wanna
- chat with an assistant
- make a picture
- make a video
- hear text read aloud
- turn a recording into text
- make music
wanna.sh runs AI on your own computer. Chat, pictures, video, voices, transcription and music in one app, private and working offline once a model is downloaded.
Six AI tools, one app
Instead of a separate app for each kind of AI, wanna.sh brings popular open models together, with the same simple controls everywhere.

Chat
Ask questions, draft emails, summarise documents and get help with code, with assistants like Qwen, Llama and Gemma.

Pictures
Describe a picture and watch it appear. Start from your own photo to restyle it.

Videos
Turn a description, or a starting picture, into a short clip.

Read aloud
Paste any text and hear it read aloud in a natural voice, then save the recording.

Transcribe
Upload a recording or use your microphone. Get a transcript with timestamps, or subtitles.

Music & sound
Describe a mood, genre or instruments and get an original piece of music.
Why run AI on your own computer?
Private by design
Your prompts, chats and creations stay on this computer. The internet is only used to find and download models.
Works offline
Once a model is downloaded it keeps working without a connection, on a plane or behind a firewall.
Free and open source
MIT licensed and developed in the open on GitHub. No accounts, no subscriptions and no per-use limits.
Uses all your hardware
Models are placed on the right graphics card automatically, and big ones are shared across several cards.
How it works
Pick a model
Browse thousands of models from Hugging Face. Each one is rated for your computer, so you know it will run before you download.
It downloads once
wanna.sh fetches only the files it needs and sets everything up. No terminals, no installers, no configuration.
Say what you want
Type a request, choose a few simple options and press Create. The model starts by itself the first time you use it.
Built for your other apps too
wanna.sh speaks the OpenAI API. Point any app, script or plugin that supports a custom OpenAI address at wanna.sh, and it uses your own models for chat, pictures, speech and transcription.
from openai import OpenAI
client = OpenAI(
base_url="http://localhost:7860/v1",
api_key="not-needed",
)
reply = client.chat.completions.create(
model="auto",
messages=[{"role": "user", "content": "Hello!"}],
)
print(reply.choices[0].message.content)
Your computer is more capable than you think.
Find a model that suits it, download it once, and start making things.
Find a model