refactor: Remove speaker mode handling from various components

abogen/web/routes.py

@@ -106,13 +106,7 @@ _CHUNK_LEVEL_OPTIONS = [
     {"value": "sentence", "label": "Sentences"},
 ]
 
-_SPEAKER_MODE_OPTIONS = [
-    {"value": "single", "label": "Single Speaker"},
-    {"value": "multi", "label": "Multi-Speaker"},
-]
-
 _CHUNK_LEVEL_VALUES = {option["value"] for option in _CHUNK_LEVEL_OPTIONS}
-_SPEAKER_MODE_VALUES = {option["value"] for option in _SPEAKER_MODE_OPTIONS}
 
 
 _DEFAULT_ANALYSIS_THRESHOLD = 3
@@ -835,7 +829,6 @@ def _prepare_speaker_metadata(
     chapters: List[Dict[str, Any]],
     chunks: List[Dict[str, Any]],
     analysis_chunks: Optional[List[Dict[str, Any]]] = None,
-    speaker_mode: str,
     voice: str,
     voice_profile: Optional[str],
     threshold: int,
@@ -848,7 +841,7 @@ def _prepare_speaker_metadata(
     chunk_list = [dict(chunk) for chunk in chunks]
     analysis_source = [dict(chunk) for chunk in (analysis_chunks or chunks)]
     threshold_value = max(1, int(threshold))
-    analysis_enabled = speaker_mode == "multi" and run_analysis
+    analysis_enabled = run_analysis
     settings_state = _load_settings()
     global_random_languages = [
         code
@@ -1323,10 +1316,7 @@ def _apply_prepare_form(
     pending.chunk_level = raw_chunk_level
     chunk_level_literal = cast(ChunkLevel, pending.chunk_level)
 
-    raw_speaker_mode = (form.get("speaker_mode") or pending.speaker_mode or "single").strip().lower()
-    if raw_speaker_mode not in _SPEAKER_MODE_VALUES:
-        raw_speaker_mode = "single"
-    pending.speaker_mode = raw_speaker_mode
+    pending.speaker_mode = "single"
 
     pending.generate_epub3 = _coerce_bool(form.get("generate_epub3"), False)
 
@@ -1660,13 +1650,12 @@ def _template_options() -> Dict[str, Any]:
         "voice_profiles": ordered_profiles,
         "voice_profile_options": profile_options,
         "separate_formats": ["wav", "flac", "mp3", "opus"],
-    "voice_catalog": voice_catalog,
-    "voice_catalog_map": {entry["id"]: entry for entry in voice_catalog},
+        "voice_catalog": voice_catalog,
+        "voice_catalog_map": {entry["id"]: entry for entry in voice_catalog},
         "sample_voice_texts": SAMPLE_VOICE_TEXTS,
         "voice_profiles_data": profiles,
         "speaker_configs": list_configs(),
         "chunk_levels": _CHUNK_LEVEL_OPTIONS,
-        "speaker_modes": _SPEAKER_MODE_OPTIONS,
         "speaker_analysis_threshold": current_settings.get(
             "speaker_analysis_threshold", _DEFAULT_ANALYSIS_THRESHOLD
         ),
@@ -1718,7 +1707,6 @@ def _settings_defaults() -> Dict[str, Any]:
         "chapter_intro_delay": 0.5,
         "max_subtitle_words": 50,
         "chunk_level": "paragraph",
-        "speaker_mode": "single",
         "generate_epub3": False,
         "speaker_analysis_threshold": _DEFAULT_ANALYSIS_THRESHOLD,
         "speaker_pronunciation_sentence": "This is {{name}} speaking.",
@@ -1788,10 +1776,6 @@ def _normalize_setting_value(key: str, value: Any, defaults: Dict[str, Any]) ->
         if isinstance(value, str) and value in _CHUNK_LEVEL_VALUES:
             return value
         return defaults[key]
-    if key == "speaker_mode":
-        if isinstance(value, str) and value in _SPEAKER_MODE_VALUES:
-            return value
-        return defaults[key]
     if key == "speaker_random_languages":
         if isinstance(value, (list, tuple, set)):
             return [code for code in value if isinstance(code, str) and code in LANGUAGE_DESCRIPTIONS]
@@ -1995,9 +1979,6 @@ def settings_page() -> ResponseReturnValue:
         updated["chunk_level"] = _normalize_setting_value(
             "chunk_level", form.get("chunk_level"), defaults
         )
-        updated["speaker_mode"] = _normalize_setting_value(
-            "speaker_mode", form.get("speaker_mode"), defaults
-        )
         updated["separate_chapters_format"] = _normalize_setting_value(
             "separate_chapters_format", form.get("separate_chapters_format"), defaults
         )
@@ -2744,11 +2725,7 @@ def enqueue_job() -> ResponseReturnValue:
     chunk_level_value = raw_chunk_level
     chunk_level_literal = cast(ChunkLevel, chunk_level_value)
 
-    speaker_mode_default = str(settings.get("speaker_mode", "single")).strip().lower()
-    raw_speaker_mode = (request.form.get("speaker_mode") or speaker_mode_default).strip().lower()
-    if raw_speaker_mode not in _SPEAKER_MODE_VALUES:
-        raw_speaker_mode = "single"
-    speaker_mode_value = raw_speaker_mode
+    speaker_mode_value = "single"
 
     generate_epub3_default = bool(settings.get("generate_epub3", False))
     generate_epub3 = _coerce_bool(request.form.get("generate_epub3"), generate_epub3_default)
@@ -2764,12 +2741,11 @@ def enqueue_job() -> ResponseReturnValue:
         maximum=25,
     )
 
-    initial_analysis = speaker_mode_value == "multi"
+    initial_analysis = False
     processed_chunks, speakers, analysis_payload, config_languages, _ = _prepare_speaker_metadata(
         chapters=selected_chapter_sources,
         chunks=raw_chunks,
         analysis_chunks=analysis_chunks,
-        speaker_mode=speaker_mode_value,
         voice=voice,
         voice_profile=selected_profile or None,
         threshold=analysis_threshold,
@@ -2868,20 +2844,6 @@ def analyze_pending_job(pending_id: str) -> ResponseReturnValue:
             )
         abort(400, message)
 
-    if pending.speaker_mode != "multi":
-        setattr(pending, "analysis_requested", False)
-        pending.chunks = []
-        pending.speaker_analysis = {}
-        error_message = "Switch to multi-speaker mode to analyze speakers."
-        if _wants_wizard_json():
-            return _wizard_json_response(
-                pending,
-                "chapters",
-                error=error_message,
-                status=400,
-            )
-        abort(400, error_message)
-
     if not enabled_overrides:
         setattr(pending, "analysis_requested", False)
         pending.chunks = []
@@ -2911,7 +2873,6 @@ def analyze_pending_job(pending_id: str) -> ResponseReturnValue:
         chapters=enabled_overrides,
         chunks=raw_chunks,
         analysis_chunks=analysis_chunks,
-        speaker_mode=pending.speaker_mode,
         voice=pending.voice,
         voice_profile=pending.voice_profile,
         threshold=pending.speaker_analysis_threshold,
@@ -2981,9 +2942,6 @@ def finalize_job(pending_id: str) -> ResponseReturnValue:
             )
         abort(400, message)
 
-    if pending.speaker_mode != "multi":
-        setattr(pending, "analysis_requested", False)
-
     if not enabled_overrides:
         pending.chunks = []
         error_message = "Select at least one chapter to convert."
@@ -3003,9 +2961,8 @@ def finalize_job(pending_id: str) -> ResponseReturnValue:
     normalized_step = _normalize_wizard_step(active_step, pending)
     raw_chunks = build_chunks_for_chapters(enabled_overrides, level=chunk_level_literal)
     analysis_chunks = build_chunks_for_chapters(enabled_overrides, level="sentence")
-    is_multi = pending.speaker_mode == "multi"
     analysis_requested = bool(getattr(pending, "analysis_requested", False))
-    should_force_entities = is_multi and normalized_step != "entities"
+    should_force_entities = analysis_requested and normalized_step != "entities"
 
     if analysis_requested:
         existing_roster: Optional[Mapping[str, Any]] = pending.speakers
@@ -3019,12 +2976,11 @@ def finalize_job(pending_id: str) -> ResponseReturnValue:
 
     config_name = pending.applied_speaker_config or selected_config
     speaker_config_payload = get_config(config_name) if config_name else None
-    run_analysis = is_multi and (should_force_entities or analysis_requested)
+    run_analysis = should_force_entities or analysis_requested
     processed_chunks, roster, analysis_payload, config_languages, updated_config = _prepare_speaker_metadata(
         chapters=enabled_overrides,
         chunks=raw_chunks,
         analysis_chunks=analysis_chunks,
-        speaker_mode=pending.speaker_mode,
         voice=pending.voice,
         voice_profile=pending.voice_profile,
         threshold=pending.speaker_analysis_threshold,
@@ -3183,8 +3139,6 @@ def _normalize_wizard_step(step: Optional[str], pending: Optional[PendingJob] =
             chosen = normalized
         else:
             chosen = default_step
-    if chosen == "entities" and pending is not None and pending.speaker_mode != "multi":
-        return "chapters"
     return chosen
 
 

abogen/web/static/prepare.js

@@ -474,38 +474,6 @@ const initPrepare = (root = document) => {
     });
   });
 
-  const speakerModeSelect = form.querySelector("#speaker_mode");
-  const analysisToggleButtons = Array.from(form.querySelectorAll('[data-step-toggle="analysis"]'));
-  const finalizeToggleButtons = Array.from(form.querySelectorAll('[data-step-toggle="finalize"]'));
-
-  const setButtonVisibility = (button, isVisible) => {
-    if (!button) return;
-    if (isVisible) {
-      button.hidden = false;
-      button.removeAttribute("aria-hidden");
-      button.removeAttribute("tabindex");
-    } else {
-      button.hidden = true;
-      button.setAttribute("aria-hidden", "true");
-      button.setAttribute("tabindex", "-1");
-    }
-  };
-
-  const updateStepButtons = () => {
-    if (!speakerModeSelect) {
-      return;
-    }
-    const modeValue = (speakerModeSelect.value || "").toLowerCase();
-    const isMulti = modeValue === "multi";
-    analysisToggleButtons.forEach((button) => setButtonVisibility(button, isMulti));
-    finalizeToggleButtons.forEach((button) => setButtonVisibility(button, !isMulti));
-  };
-
-  if (speakerModeSelect) {
-    updateStepButtons();
-    speakerModeSelect.addEventListener("change", updateStepButtons);
-  }
-
   const voiceModal = document.querySelector('[data-role="voice-modal"]');
   let activeGenderFilter = "";
 

abogen/web/static/wizard.js

@@ -273,7 +273,18 @@ const submitWizardForm = async (form, submitter) => {
   }
   const action = submitter?.getAttribute("formaction") || form.getAttribute("action") || window.location.href;
   const method = (submitter?.getAttribute("formmethod") || form.getAttribute("method") || "GET").toUpperCase();
+  const stepTarget = submitter?.dataset?.stepTarget || "";
+  const normalizedStepTarget = stepTarget ? stepTarget.toLowerCase() : "";
+  if (normalizedStepTarget) {
+    const activeInput = form.querySelector('[data-role="active-step-input"]');
+    if (activeInput) {
+      activeInput.value = normalizedStepTarget;
+    }
+  }
   const formData = new FormData(form);
+  if (normalizedStepTarget) {
+    formData.set("active_step", normalizedStepTarget);
+  }
   if (submitter && submitter.name && !formData.has(submitter.name)) {
     formData.append(submitter.name, submitter.value ?? "");
   }

abogen/web/templates/job_detail.html

@@ -27,7 +27,6 @@
         <li><strong>Max words per subtitle:</strong> {{ job.max_subtitle_words }}</li>
         <li><strong>Project folder:</strong> {{ 'Yes' if job.save_as_project else 'No' }}</li>
         <li><strong>Chunk granularity:</strong> {{ job.chunk_level|replace('_', ' ')|title }}</li>
-        <li><strong>Speaker mode:</strong> {{ job.speaker_mode|replace('_', ' ')|title }}</li>
         <li><strong>Speaker analysis threshold:</strong> {{ job.speaker_analysis_threshold }}</li>
         <li><strong>Generate EPUB 3:</strong> {{ 'Yes' if job.generate_epub3 else 'No' }}</li>
       </ul>

abogen/web/templates/partials/new_job_step_book.html

@@ -31,14 +31,6 @@
 {% else %}
   {% set generate_epub3 = pending.generate_epub3 if pending else settings_dict.get('generate_epub3', False) %}
 {% endif %}
-{% set speaker_mode_value = form_values.get('speaker_mode') if form_values else None %}
-{% if not speaker_mode_value %}
-  {% if pending and pending.speaker_mode %}
-    {% set speaker_mode_value = pending.speaker_mode %}
-  {% else %}
-    {% set speaker_mode_value = settings_dict.get('speaker_mode', 'single') %}
-  {% endif %}
-{% endif %}
 {% set chunk_level_value = form_values.get('chunk_level') if form_values else None %}
 {% if not chunk_level_value %}
   {% if pending and pending.chunk_level %}
@@ -247,25 +239,15 @@
     <section class="form-section">
       <h3 class="form-section__title">Entities &amp; casting</h3>
       <div class="form-section__layout">
-        <div class="field-grid field-grid--two">
-          <div class="field field--stack">
-            <label for="speaker_config">Speaker preset</label>
-            <select id="speaker_config" name="speaker_config" {{ 'disabled' if readonly else '' }}>
-              <option value="">None</option>
-              {% for config in options.speaker_configs %}
-              <option value="{{ config.name }}" {% if selected_config == config.name %}selected{% endif %}>{{ config.name }} · {{ config.speakers|length }} speaker{% if config.speakers|length != 1 %}s{% endif %}</option>
-              {% endfor %}
-            </select>
-            <p class="hint">Reuse a saved roster to keep character voices consistent.</p>
-          </div>
-          <div class="field">
-            <label for="speaker_mode">Speaker mode</label>
-            <select id="speaker_mode" name="speaker_mode" {{ 'disabled' if readonly else '' }}>
-              {% for option in options.speaker_modes %}
-              <option value="{{ option.value }}" {% if speaker_mode_value == option.value %}selected{% endif %}>{{ option.label }}</option>
-              {% endfor %}
-            </select>
-          </div>
+        <div class="field field--stack">
+          <label for="speaker_config">Speaker preset</label>
+          <select id="speaker_config" name="speaker_config" {{ 'disabled' if readonly else '' }}>
+            <option value="">None</option>
+            {% for config in options.speaker_configs %}
+            <option value="{{ config.name }}" {% if selected_config == config.name %}selected{% endif %}>{{ config.name }} · {{ config.speakers|length }} speaker{% if config.speakers|length != 1 %}s{% endif %}</option>
+            {% endfor %}
+          </select>
+          <p class="hint">Reuse a saved roster to keep character voices consistent.</p>
         </div>
         <div class="field-grid field-grid--two">
           <div class="field">

abogen/web/templates/partials/new_job_step_chapters.html

@@ -1,4 +1,3 @@
-{% set is_multi_speaker = pending.speaker_mode == 'multi' %}
 <form method="post"
   action="{{ url_for('web.finalize_job', pending_id=pending.id) }}"
   class="prepare-form"
@@ -7,12 +6,10 @@
   data-wizard-form="true"
   data-step="chapters"
   data-pending-id="{{ pending.id }}"
-  data-speaker-mode="{{ pending.speaker_mode }}"
   data-analyze-url="{{ url_for('web.analyze_pending_job', pending_id=pending.id) }}">
   <input type="hidden" name="active_step" value="chapters" data-role="active-step-input">
   <div class="wizard-hidden-inputs" aria-hidden="true">
     <input type="hidden" name="chunk_level" value="{{ pending.chunk_level }}">
-    <input type="hidden" name="speaker_mode" value="{{ pending.speaker_mode }}">
     <input type="hidden" name="speaker_analysis_threshold" value="{{ pending.speaker_analysis_threshold }}">
     <input type="hidden" name="chapter_intro_delay" value="{{ '%.2f'|format(pending.chapter_intro_delay) }}">
     {% if pending.generate_epub3 %}

abogen/web/templates/partials/new_job_step_entities.html

@@ -1,4 +1,3 @@
-{% set is_multi_speaker = pending.speaker_mode == 'multi' %}
 {% set embed_scripts = embed_scripts if embed_scripts is defined else True %}
 <form method="post"
       action="{{ url_for('web.finalize_job', pending_id=pending.id) }}"
@@ -8,7 +7,6 @@
   data-wizard-form="true"
   data-step="entities"
   data-pending-id="{{ pending.id }}"
-      data-speaker-mode="{{ pending.speaker_mode }}"
       data-analyze-url="{{ url_for('web.analyze_pending_job', pending_id=pending.id) }}"
       data-entities-url="{{ url_for('api.api_pending_entities', pending_id=pending.id) }}"
       data-manual-list-url="{{ url_for('api.api_list_manual_overrides', pending_id=pending.id) }}"

abogen/web/templates/settings.html

@@ -23,14 +23,6 @@
         </select>
         <p class="hint">Used whenever “Standard voice” is selected for a new job.</p>
       </div>
-      <div class="field">
-        <label for="speaker_mode_default">Speaker Mode</label>
-        <select id="speaker_mode_default" name="speaker_mode">
-          {% for option in options.speaker_modes %}
-          <option value="{{ option.value }}" {% if settings.speaker_mode == option.value %}selected{% endif %}>{{ option.label }}</option>
-          {% endfor %}
-        </select>
-      </div>
       <div class="field">
         <label for="chunk_level_default">Chunk Granularity</label>
         <select id="chunk_level_default" name="chunk_level">