{# Settings → LLM transcript enhancement (issues #10/#46): the tri-state endpoint/key form. Self-contained — renders from _settings_context, POSTs to /settings/llm with its own CSRF token. #}

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 %}