{% extends "base.html" %} {% block title %}abogen · Settings{% endblock %} {% block content %}

Application Settings

Settings apply to new jobs you queue from the dashboard.

{% if saved %}
Settings saved successfully.
{% endif %} {% with messages = get_flashed_messages(with_categories=True) %} {% if messages %} {% for category, message in messages %}
{{ message }}
{% endfor %} {% endif %} {% endwith %}
Narration Defaults

Pick a saved speaker from Speaker Studio to use by default for new jobs.

Kokoro settings

Used when no default speaker is selected, and as a fallback when speaker analysis cannot resolve a speaker.

Supertonic settings

These defaults apply when a Supertonic speaker does not override them.

2 = fastest/lowest quality, 15 = slowest/highest quality.

Speakers detected fewer times fall back to the narrator voice.

Include {{ '{{name}}' }} where the speaker name should be inserted.

Disable if you prefer to skip entity extraction in the job wizard.

{% set selected_languages = settings.speaker_random_languages or [] %}

Limits random voice selection for speakers marked as random. Leave empty to allow any language.

Audio & Delivery

Default output: {{ default_output_dir }}

Inserted between the spoken chapter title and the chapter content. Set to 0 to disable.

When enabled, the narrator speaks the title, optional subtitle, and author names before chapter one.

Adds a brief "The end" line after the final chapter, optionally including series information.

Converts screaming uppercase openings to sentence case while preserving acronyms.

Ensures the spoken chapter heading starts with "Chapter" when source titles begin with only a number or numeral.

Subtitles & Text
Performance
Endpoint

Point to an OpenAI-compatible endpoint such as Ollama or a proxy.

Leave blank or use ollama for local servers that do not require keys.

Normalization Prompt

Use {{ '{{sentence}}' }} for the active sentence. {{ '{{paragraph}}' }} remains available for legacy prompts.

Context Mode
{% for option in llm_context_options %} {% endfor %}
{% for group in options.normalization_groups %}
{{ group.label }} {% if group.label == "Apostrophes & Contractions" %}
Strategy
{% for option in apostrophe_modes %} {% endfor %}
{% if settings.normalization_apostrophe_mode == 'llm' and not llm_ready %}

Configure the LLM connection before using it for audiobook runs.

{% endif %}
{% endif %}
{% for option in group.options %} {% endfor %}
{% if group.label == "Apostrophes & Contractions" %}

Choose which contraction families are expanded.

{% endif %}
{% endfor %}
Sample & Preview

              
            
Calibre OPDS

Leave blank to keep the stored password.

Audiobookshelf

Use the server root (no trailing /api); the upload requests add it automatically.

Enter the folder exactly as it appears in Audiobookshelf, paste the folder ID, or browse the available folders.

Leave blank to keep the stored token.

Debug · TTS transformations

Generate a set of WAV files from a purpose-built EPUB containing code-tagged examples. When something sounds wrong, report the code (e.g. NUM_001) to pinpoint the failing transformation.

Uses your current Settings defaults (voice, language, speed, GPU). If generation fails, an error will appear at the top of this page.

{% if debug_manifest and debug_manifest.artifacts %}
{% endif %} {% if debug_samples %}
    {% for sample in debug_samples %}
  • {{ sample.code }} — {{ sample.label }}: {{ sample.text }}
  • {% endfor %}
{% endif %}
{% endblock %} {% block scripts %} {{ super() }} {% endblock %}