{% extends "base.html" %} {% block title %}Voxint — settings{% endblock %} {% block body %}

Settings

{% if tutorial_done %} {# Completion celebration after POST /settings/tutorial/complete (?tutorial=done). Terminal — no "next step" — so it is rendered here rather than through the walkthrough banner partial, and it offers the plain "submit your own media" link the plan calls for in place of a live "try it" step. #}

You finished the tutorial 🎉

You have completed one full run end to end — submit, review, attribute, export. When you are ready, submit your own audio or video and do the same with real speakers.

{% endif %}

First-run setup

Onboarding is complete. You can walk through the setup wizard again at any time — it never resets your existing preferences unless you change them.

Re-run the setup wizard →

LLM transcript enhancement (optional)

When enabled, Voxint sends transcript segments to an OpenAI-compatible model to clean them up and surface likely speaker names. It's best-effort — a slow or failing model never blocks a run. Changes take effect on your next run or enrichment job, no restart needed.

{% if llm_error %} {% endif %} {% if llm_key_present %} {% if llm_key_source == "stored" %}

An API key is saved here. ✓ (stored)

{% else %}

An LLM_API_KEY is set in the environment. ✓ (environment)

{% endif %} {% else %}

No API key is configured. Enter one below (or set LLM_API_KEY in the environment) before enabling.

{% endif %} {% if not llm_budget_ok %}

The configured LLM run budget doesn't fit the transcription stage lease, so enhancement can't be enabled until that's adjusted.

{% endif %}

Stored in Voxint's database and used for all LLM features. Never shown again after saving.

{% if llm_key_source == "stored" %}
{% endif %}

Guided tutorial

{% if not tutorial_available %}

The guided tutorial isn't set up yet. Run voxint tutorial seed to create the bundled three-speaker sample, then reload this page.

{% elif tutorial_completed_at %}

Completed {{ tutorial_completed_at.strftime("%Y-%m-%d %H:%M") }}.

Replaying walks you through the sample again. Your previous speaker rulings on the tutorial run are preserved — replay doesn't reset them.

{% else %}

A short, hands-on walkthrough of one full run on a bundled three-speaker sample.

Start the guided tutorial →

{% endif %}
{% endblock %}