{% extends "base.html" %} {% block title %}Audio generation · {{ profile.name }}{% endblock %} {% block content %}

Audio generation benchmark · {{ profile.name }}

Benchmarks a music/sound-effect generation model's real-time-factor (Lemonade's acestep/thinksound recipes, /v1/audio/generations -- not speech; see Text-to-speech for that). Deliberately separate from the model/router leaderboard and from TTS results -- generating music is a different task with a different compute profile. This runs synchronously.

{% if capabilities.error %}

Couldn't reach this instance ({{ capabilities.error }}) -- engine and backend fall back to free text.

{% endif %}
{% if audiogen_models %} {% else %}
No audio-generation models pulled yet on this profile -- pull one via lemonmatrix profile pull-model (recipe acestep), then reload this page.
{% endif %}
{% if audiogen_backends %} {% else %}
No audio-generation backend detected -- install it on the profile page first, or enter it manually.
{% endif %}
{% if default_os %}
{{ default_os }} (fixed by this profile)
{% else %}
Couldn't detect -- see profile page to fix discovery.
{% endif %}

Audio-gen results for {{ profile.name }}

{% if not results %}

No audio-generation results yet.

{% else %}
{% for r in results %} {% endfor %}
TimestampModelGeneration (ms)Audio (s)RTFValidNotes
{{ r.timestamp }} {{ r.model.name }} {{ "%.1f"|format(r.metrics.generation_time_ms) }} {{ "%.2f"|format(r.metrics.audio_duration_s) }} {{ "%.2f"|format(r.metrics.real_time_factor) }}x {{ "valid" if r.validity.valid else "invalid" }} {{ r.validity.notes or "" }}
{% endif %}
{% endblock %}