Set up VoiceStudio on this VM by following the exe.dev recipe at https://exe.dev/deploy/voicestudio.md from top to bottom.

The recipe's example VM name is my-voicestudio. This VM's name is the output of `hostname`: use it wherever the recipe writes my-voicestudio. Skip the step that creates the VM; you are on it.

This recipe needs a 60GB disk, and a new VM's may be smaller. Before you install anything, run `df -h /`. If its size is under 54G, stop and ask me to grow the disk, either with this link: https://exe.dev/suggest?command=resize%20my-voicestudio%20--disk%3D60GB or, on my computer, with `ssh exe.dev resize my-voicestudio --disk=60GB`. When I say it's done, run `sudo resize2fs "$(findmnt -no SOURCE /)"`, check `df -h /` again, and carry on.

You are done when all of these are true. Check each one yourself:
- VoiceStudio at the VM's private URL, locked with an API key kept in ~/voicestudio/.env.
- Speech and transcription on the VM's CPU, checked with a short test clip.
- Voices, projects, settings and models on the VM's disk, kept across restarts and updates.
- Starts again after a reboot; nightly backups, with one checked.

Read the whole recipe, including the closed details. For initial setup,
follow "Install by hand", skipping VM creation and SSH: room on the disk,
Docker, Start VoiceStudio, Check speech, the backup timer and the backup
check. The walkthrough at the top is for the owner afterwards. Do not run
Restore or Update.
Work as exedev in ~/voicestudio. Never overwrite an existing .env.
Do not accept any model licence for the owner, and do not run the
first-run wizard in a browser: the owner does both. Do not share the VM
or make it public.
Verify docker.service is enabled and the container uses unless-stopped;
do not reboot. Finish with the studio URL and the command from "Open the
studio" that prints the API key; don't paste the key into the chat.

Finish with the URLs I should open.