{% extends "base.html" %} {% block title %}Text-to-speech · {{ profile.name }}{% endblock %} {% block content %}

Text-to-speech benchmark · {{ profile.name }}

Benchmarks a TTS model's real-time-factor (Lemonade's kokoro/openmoss recipes, /v1/audio/speech). Deliberately separate from the model/router leaderboard -- real-time-factor isn't comparable to LLM token throughput. This runs synchronously.

{% if capabilities.error %}

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

{% endif %}
{% if tts_models %} {% else %}
No TTS models pulled yet on this profile -- pull one via lemonmatrix profile pull-model (recipe kokoro), then reload this page.
{% endif %}
{% if tts_backends %} {% else %}
No TTS 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 %}

TTS results for {{ profile.name }}

{% if not results %}

No TTS results yet.

{% else %}
{% for r in results %} {% endfor %}
TimestampModelGeneration (ms)Audio (s)RTFVoiceValidNotes
{{ 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 {{ r.metrics.voice or "–" }} {{ "valid" if r.validity.valid else "invalid" }} {{ r.validity.notes or "" }}
{% endif %}
{% endblock %}