{% extends "base.html" %} {% set labels = { "welcome": "Welcome", "media": "Media folders", "vocabulary": "Vocabulary", "llm": "Text clean-up and name hints (optional)", "services": "Readiness", "finish": "Finish", } %} {% block title %}Voxint setup — {{ labels[step.value] }}{% endblock %} {# The wizard runs before onboarding, so the protected top nav (Runs / Review) would only bounce the operator back here. Replace it with a step indicator. #} {% block nav %}
Voxint transcribes your audio and video, separates who spoke when, and lets you attribute each voice to a real person, so you get a searchable, speaker-labelled transcript you can trust.
This quick setup takes about two minutes. Every step is optional and you can revisit it later.
{% elif step.value == "media" %}Voxint reads media from under {{ media_root }}. Browse to the folders
you want it to watch and add them; optionally choose a domain pack per folder to
tune transcription and enrichment. You can skip this and submit files individually
later.
Optionally look through your registered folders for audio/video that isn't in Voxint yet, and queue it for transcription.
{% elif step.value == "vocabulary" %}Add names, jargon, acronyms, and preferred spellings — one per line. Voxint feeds these to transcription and to name attribution, so unusual terms come out right. They apply to your next run with no restart needed.
{% elif step.value == "llm" %}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; enhancement is simply skipped.
{% 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)
No API key is configured. Enter one below (or set
LLM_API_KEY in the environment) before enabling.
The configured LLM run budget doesn't fit the transcription stage lease, so enhancement can't be enabled until that's adjusted.
{% endif %} {% elif step.value == "services" %}Voxint's transcription, diarization, and speaker-embedding run as separate model services (GPU or CPU tier), backed by Postgres and Redis. Here's whether each dependency is reachable right now: ready means good to go, failed means the pipeline can't run until you fix it, and unverified means an optional feature couldn't be confirmed:
{% for check in doctor_checks %}{{ check.remediation }}
{% endif %} {% endfor %}If a service is down, start the model services — the GPU overlay
(compose.gpu.yaml) or, with no NVIDIA GPU, the CPU overlay
(compose.cpu.yaml); see the README's quickstart. This check is advisory —
you can finish setup regardless. But a run submitted while a service it needs is down
will retry with backoff (about five attempts over roughly an hour and a half) and then
land failed; once the services are up, requeue it from the run's
page.
{{ tutorial_error }}
{% endif %}The guided tutorial is a short, hands-on walkthrough of one full run on a bundled three-speaker sample — the quickest way to learn the console. You can re-run this setup, or the tutorial, any time from Settings.
The tutorial's bundled sample is set up the first time you start it — no command line needed.
{% endif %} {% endif %}