feat/frontend-phase1 #1

Merged
stwhite merged 34 commits from feat/frontend-phase1 into main 2025-08-14 15:44:25 +00:00
3 changed files with 280 additions and 0 deletions
Showing only changes of commit d8eb2492d7 - Show all commits

102
CLAUDE.md Normal file
View File

@ -0,0 +1,102 @@
# CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
## Common Development Commands
### Backend (FastAPI)
```bash
# Install backend dependencies (run from project root)
pip install -r backend/requirements.txt
# Run backend development server (run from project root)
uvicorn backend.app.main:app --reload --host 0.0.0.0 --port 8000
# Run backend tests
python backend/run_api_test.py
# Backend API accessible at http://127.0.0.1:8000
# API docs at http://127.0.0.1:8000/docs
```
### Frontend Testing
```bash
# Run frontend tests
npm test
```
### Alternative Interfaces
```bash
# Run Gradio interface (standalone TTS app)
python gradio_app.py
```
## Architecture Overview
This is a full-stack TTS (Text-to-Speech) application with three interfaces:
1. **Modern web frontend** (vanilla JS) - Interactive dialog editor at `frontend/`
2. **FastAPI backend** - REST API at `backend/`
3. **Gradio interface** - Alternative UI in `gradio_app.py`
### Frontend-Backend Communication
- **Frontend**: Vanilla JS (ES6 modules) serving on port 8001
- **Backend**: FastAPI serving on port 8000
- **API Base**: `http://localhost:8000/api`
- **CORS**: Configured for frontend communication
- **File Serving**: Generated audio served via `/generated_audio/` endpoint
### Key API Endpoints
- `/api/speakers/` - Speaker CRUD operations
- `/api/dialog/generate/` - Full dialog generation
- `/api/dialog/generate_line/` - Single line generation
- `/generated_audio/` - Static audio file serving
### Backend Service Architecture
Located in `backend/app/services/`:
- **TTSService**: Chatterbox TTS model lifecycle management
- **SpeakerManagementService**: Speaker data and sample management
- **DialogProcessorService**: Dialog script to audio processing
- **AudioManipulationService**: Audio concatenation and ZIP creation
### Frontend Architecture
- **Modular design**: `api.js` (API layer) + `app.js` (app logic)
- **No framework**: Modern vanilla JavaScript with ES6+ features
- **Interactive editor**: Table-based dialog creation with drag-drop reordering
### Data Flow
1. User creates dialog in frontend table editor
2. Frontend sends dialog items to `/api/dialog/generate/`
3. Backend processes speech/silence items via services
4. TTS generates audio, segments concatenated
5. ZIP archive created with all outputs
6. Frontend receives URLs for playback/download
### Speaker Configuration
- **Location**: `speaker_data/speakers.yaml` and `speaker_data/speaker_samples/`
- **Format**: YAML config referencing WAV audio samples
- **Management**: Both API endpoints and file-based configuration
### Output Organization
- `dialog_output/` - Generated dialog files
- `single_output/` - Single utterance outputs
- `tts_outputs/` - Raw TTS generation files
- Generated ZIPs contain organized file structure
## Development Setup Notes
- Python virtual environment expected at project root (`.venv`)
- Backend commands run from project root, not `backend/` directory
- Frontend served separately (typically port 8001)
- Speaker samples must be WAV format in `speaker_data/speaker_samples/`

View File

@ -43,6 +43,11 @@
<label for="output-base-name">Output Base Name:</label>
<input type="text" id="output-base-name" name="output-base-name" value="dialog_output" required>
</div>
<div class="dialog-controls form-row">
<button id="save-script-btn">Save Script</button>
<input type="file" id="load-script-input" accept=".jsonl" style="display: none;">
<button id="load-script-btn">Load Script</button>
</div>
<button id="generate-dialog-btn">Generate Dialog</button>
</section>
</div>

View File

@ -125,6 +125,9 @@ function initializeDialogEditor() {
const addSilenceLineBtn = document.getElementById('add-silence-line-btn');
const outputBaseNameInput = document.getElementById('output-base-name');
const generateDialogBtn = document.getElementById('generate-dialog-btn');
const saveScriptBtn = document.getElementById('save-script-btn');
const loadScriptBtn = document.getElementById('load-script-btn');
const loadScriptInput = document.getElementById('load-script-input');
// Results Display Elements
const generationLogPre = document.getElementById('generation-log-content'); // Corrected ID
@ -507,6 +510,176 @@ function initializeDialogEditor() {
});
}
// --- Save/Load Script Functionality ---
function saveDialogScript() {
if (dialogItems.length === 0) {
alert('No dialog items to save. Please add some speech or silence lines first.');
return;
}
// Filter out UI-specific fields and create clean data for export
const exportData = dialogItems.map(item => {
const cleanItem = {
type: item.type
};
if (item.type === 'speech') {
cleanItem.speaker_id = item.speaker_id;
cleanItem.text = item.text;
} else if (item.type === 'silence') {
cleanItem.duration = item.duration;
}
return cleanItem;
});
// Convert to JSONL format (one JSON object per line)
const jsonlContent = exportData.map(item => JSON.stringify(item)).join('\n');
// Create and download file
const blob = new Blob([jsonlContent], { type: 'application/jsonl' });
const url = URL.createObjectURL(blob);
const link = document.createElement('a');
// Generate filename with timestamp
const timestamp = new Date().toISOString().replace(/[:.]/g, '-').slice(0, 19);
const filename = `dialog_script_${timestamp}.jsonl`;
link.href = url;
link.download = filename;
link.style.display = 'none';
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
URL.revokeObjectURL(url);
console.log(`Dialog script saved as ${filename}`);
}
function loadDialogScript(file) {
if (!file) {
alert('Please select a file to load.');
return;
}
const reader = new FileReader();
reader.onload = function(e) {
try {
const content = e.target.result;
const lines = content.trim().split('\n');
const loadedItems = [];
for (let i = 0; i < lines.length; i++) {
const line = lines[i].trim();
if (!line) continue; // Skip empty lines
try {
const item = JSON.parse(line);
const validatedItem = validateDialogItem(item, i + 1);
if (validatedItem) {
loadedItems.push(normalizeDialogItem(validatedItem));
}
} catch (parseError) {
console.error(`Error parsing line ${i + 1}:`, parseError);
alert(`Error parsing line ${i + 1}: ${parseError.message}`);
return;
}
}
if (loadedItems.length === 0) {
alert('No valid dialog items found in the file.');
return;
}
// Confirm replacement if existing items
if (dialogItems.length > 0) {
const confirmed = confirm(
`This will replace your current dialog (${dialogItems.length} items) with the loaded script (${loadedItems.length} items). Continue?`
);
if (!confirmed) return;
}
// Replace current dialog
dialogItems.splice(0, dialogItems.length, ...loadedItems);
renderDialogItems();
console.log(`Loaded ${loadedItems.length} dialog items from script`);
alert(`Successfully loaded ${loadedItems.length} dialog items.`);
} catch (error) {
console.error('Error loading dialog script:', error);
alert(`Error loading dialog script: ${error.message}`);
}
};
reader.onerror = function() {
alert('Error reading file. Please try again.');
};
reader.readAsText(file);
}
function validateDialogItem(item, lineNumber) {
if (!item || typeof item !== 'object') {
throw new Error(`Line ${lineNumber}: Invalid item format`);
}
if (!item.type || !['speech', 'silence'].includes(item.type)) {
throw new Error(`Line ${lineNumber}: Invalid or missing type. Must be 'speech' or 'silence'`);
}
if (item.type === 'speech') {
if (!item.speaker_id || typeof item.speaker_id !== 'string') {
throw new Error(`Line ${lineNumber}: Speech items must have a valid speaker_id`);
}
if (!item.text || typeof item.text !== 'string') {
throw new Error(`Line ${lineNumber}: Speech items must have text`);
}
// Check if speaker exists in available speakers
const speakerExists = availableSpeakersCache.some(speaker => speaker.id === item.speaker_id);
if (availableSpeakersCache.length > 0 && !speakerExists) {
console.warn(`Line ${lineNumber}: Speaker '${item.speaker_id}' not found in available speakers`);
// Don't throw error, just warn - speaker might be added later
}
return {
type: 'speech',
speaker_id: item.speaker_id,
text: item.text
};
} else if (item.type === 'silence') {
if (typeof item.duration !== 'number' || item.duration <= 0) {
throw new Error(`Line ${lineNumber}: Silence items must have a positive duration number`);
}
return {
type: 'silence',
duration: item.duration
};
}
}
// Event handlers for save/load
if (saveScriptBtn) {
saveScriptBtn.addEventListener('click', saveDialogScript);
}
if (loadScriptBtn && loadScriptInput) {
loadScriptBtn.addEventListener('click', () => {
loadScriptInput.click();
});
loadScriptInput.addEventListener('change', (e) => {
const file = e.target.files[0];
if (file) {
loadDialogScript(file);
// Reset input so same file can be loaded again
e.target.value = '';
}
});
}
console.log('Dialog Editor Initialized');
renderDialogItems(); // Initial render (empty)
}