Add long text splitting and update to v3.2.0

Introduces long text splitting functionality to TTSFM, allowing automatic chunking and speech generation for texts exceeding the character limit. Updates CLI, Python API, and web app to use the new methods, expands supported voices, and improves documentation and UI. Bumps version to 3.2.0 and refines styles and feature descriptions.

Author: dbccccccc

example_long_text.py

@@ -0,0 +1,76 @@
+#!/usr/bin/env python3
+"""
+Example demonstrating long text splitting functionality in TTSFM.
+
+This example shows how to use the new long text methods to automatically
+split and generate speech from text longer than the 4096 character limit.
+"""
+
+from ttsfm import TTSClient, Voice, AudioFormat
+
+def main():
+    # Create a long text example (over 4096 characters)
+    long_text = """
+    This is a demonstration of the TTSFM long text functionality. 
+    When you have text that exceeds the 4096 character limit, TTSFM can 
+    automatically split it into smaller chunks and generate speech for each chunk.
+    
+    The text splitting is intelligent - it preserves word boundaries by default,
+    so you won't get words cut off in the middle. This ensures natural-sounding
+    speech across all generated audio files.
+    
+    You can use this functionality in several ways:
+    
+    1. Using the TTSClient.generate_speech_long_text() method
+    2. Using the TTSClient.generate_speech_batch() method (alias)
+    3. Using the convenience function generate_speech_long_text()
+    4. Using the CLI with the --split-long-text flag
+    
+    The method returns a list of TTSResponse objects, one for each chunk.
+    You can then save each response to a separate file, or combine them
+    if needed for your use case.
+    
+    This feature is particularly useful for:
+    - Converting long articles or documents to speech
+    - Processing book chapters or large text files
+    - Generating audio for educational content
+    - Creating podcasts or audiobooks from text
+    
+    The splitting algorithm is designed to be smart about where it breaks
+    the text, preferring to split at sentence boundaries when possible,
+    and always preserving word boundaries unless explicitly disabled.
+    """ * 10  # Repeat to make it definitely over 4096 characters
+
+    print(f"Text length: {len(long_text)} characters")
+    print("Generating speech from long text...\n")
+
+    # Create client
+    client = TTSClient()
+
+    try:
+        # Method 1: Using generate_speech_long_text
+        print("Method 1: Using generate_speech_long_text()")
+        responses = client.generate_speech_long_text(
+            text=long_text,
+            voice=Voice.ALLOY,
+            response_format=AudioFormat.MP3,
+            max_length=2000,  # Smaller chunks for demo
+            preserve_words=True
+        )
+        
+        print(f"Generated {len(responses)} audio chunks")
+        
+        # Save each chunk
+        for i, response in enumerate(responses, 1):
+            filename = f"long_text_part_{i:03d}.mp3"
+            response.save_to_file(filename)
+            print(f"Saved: {filename}")
+        
+        print(f"\nTotal audio files generated: {len(responses)}")
+        print("You can play these files in sequence to hear the complete text.")
+        
+    except Exception as e:
+        print(f"Error: {e}")
+
+if __name__ == "__main__":
+    main()

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "ttsfm"
-version = "3.1.0"
+version = "3.2.0"
 description = "Text-to-Speech API Client with OpenAI compatibility"
 readme = "README.md"
 license = "MIT"

ttsfm-web/app.py

@@ -310,50 +310,50 @@ def generate_speech_batch():
         except ValueError as e:
             return jsonify({"error": f"Invalid voice or format: {e}"}), 400
 
-        # Split text into chunks
-        chunks = split_text_by_length(text, max_length, preserve_words)
-
-        if not chunks:
+        # Use the new long text method
+        try:
+            responses = tts_client.generate_speech_long_text(
+                text=text,
+                voice=voice_enum,
+                response_format=format_enum,
+                instructions=instructions,
+                max_length=max_length,
+                preserve_words=preserve_words
+            )
+        except Exception as e:
+            logger.error(f"Long text generation failed: {e}")
+            return jsonify({"error": f"Long text generation failed: {str(e)}"}), 500
+
+        if not responses:
             return jsonify({"error": "No valid text chunks found"}), 400
 
-        logger.info(f"Processing {len(chunks)} chunks for batch generation")
+        logger.info(f"Generated {len(responses)} chunks for batch generation")
 
-        # Generate speech for each chunk
+        # Process responses
         results = []
-        for i, chunk in enumerate(chunks):
+        for i, response in enumerate(responses):
             try:
-                response = tts_client.generate_speech(
-                    text=chunk,
-                    voice=voice_enum,
-                    response_format=format_enum,
-                    instructions=instructions,
-                    max_length=max_length,
-                    validate_length=False  # Already split
-                )
-
                 # Convert to base64 for JSON response
                 import base64
                 audio_b64 = base64.b64encode(response.audio_data).decode('utf-8')
 
                 results.append({
                     "chunk_index": i + 1,
-                    "chunk_text": chunk[:100] + "..." if len(chunk) > 100 else chunk,
                     "audio_data": audio_b64,
                     "content_type": response.content_type,
                     "size": response.size,
                     "format": response.format.value
                 })
 
             except Exception as e:
-                logger.error(f"Failed to generate chunk {i+1}: {e}")
+                logger.error(f"Failed to process chunk {i+1}: {e}")
                 results.append({
                     "chunk_index": i + 1,
-                    "chunk_text": chunk[:100] + "..." if len(chunk) > 100 else chunk,
                     "error": str(e)
                 })
 
         return jsonify({
-            "total_chunks": len(chunks),
+            "total_chunks": len(responses),
             "successful_chunks": len([r for r in results if "audio_data" in r]),
             "results": results
         })
@@ -376,7 +376,7 @@ def get_status():
         return jsonify({
             "status": "online",
             "tts_service": "openai.fm (free)",
-            "package_version": "3.0.0",
+            "package_version": "3.2.0",
             "timestamp": datetime.now().isoformat()
         })
 

ttsfm-web/static/css/style.css

@@ -2,25 +2,25 @@
 
 :root {
     /* Clean Color Palette */
-    --primary-color: #2563eb;
-    --primary-dark: #1d4ed8;
-    --primary-light: #3b82f6;
-    --secondary-color: #64748b;
-    --secondary-dark: #475569;
-    --accent-color: #10b981;
-    --accent-dark: #059669;
+    --primary-color: #4f46e5;
+    --primary-dark: #3730a3;
+    --primary-light: #6366f1;
+    --secondary-color: #6b7280;
+    --secondary-dark: #4b5563;
+    --accent-color: #059669;
+    --accent-dark: #047857;
 
     /* Status Colors */
-    --success-color: #10b981;
-    --warning-color: #f59e0b;
-    --danger-color: #ef4444;
-    --info-color: #3b82f6;
+    --success-color: #059669;
+    --warning-color: #d97706;
+    --danger-color: #dc2626;
+    --info-color: #2563eb;
 
     /* Clean Neutral Colors */
     --light-color: #ffffff;
-    --light-gray: #f8fafc;
-    --medium-gray: #64748b;
-    --dark-color: #1e293b;
+    --light-gray: #f9fafb;
+    --medium-gray: #6b7280;
+    --dark-color: #111827;
     --text-color: #374151;
     --text-muted: #6b7280;
 
@@ -75,33 +75,38 @@ h1, h2, h3, h4, h5, h6 {
 /* Simplified Button Styles */
 .btn {
     font-weight: 600;
-    border-radius: var(--border-radius-sm);
-    transition: all 0.2s ease;
+    border-radius: 12px;
+    transition: all 0.3s ease;
     letter-spacing: 0.025em;
+    border: none;
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
 }
 
 .btn-primary {
-    background-color: var(--primary-color);
-    border-color: var(--primary-color);
+    background: linear-gradient(135deg, var(--primary-color) 0%, var(--primary-light) 100%);
     color: white;
 }
 
 .btn-primary:hover {
-    background-color: var(--primary-dark);
-    border-color: var(--primary-dark);
+    background: linear-gradient(135deg, var(--primary-dark) 0%, var(--primary-color) 100%);
     color: white;
+    transform: translateY(-1px);
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.15);
 }
 
 .btn-outline-primary {
     border: 2px solid var(--primary-color);
     color: var(--primary-color);
     background: transparent;
+    box-shadow: none;
 }
 
 .btn-outline-primary:hover {
     background: var(--primary-color);
     border-color: var(--primary-color);
     color: white;
+    transform: translateY(-1px);
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.15);
 }
 
 .btn-lg {
@@ -119,15 +124,16 @@ h1, h2, h3, h4, h5, h6 {
 /* Clean Card Styles */
 .card {
     border: 1px solid #e5e7eb;
-    box-shadow: 0 1px 2px rgba(0, 0, 0, 0.05);
-    transition: all 0.2s ease;
-    border-radius: 12px;
+    box-shadow: 0 1px 3px rgba(0, 0, 0, 0.1);
+    transition: all 0.3s ease;
+    border-radius: 16px;
     background: white;
 }
 
 .card:hover {
-    box-shadow: 0 4px 6px rgba(0, 0, 0, 0.07);
-    border-color: #d1d5db;
+    box-shadow: 0 10px 25px rgba(0, 0, 0, 0.1);
+    border-color: var(--primary-light);
+    transform: translateY(-2px);
 }
 
 .card-body {
@@ -136,10 +142,10 @@ h1, h2, h3, h4, h5, h6 {
 
 /* Clean Hero Section */
 .hero-section {
-    background: linear-gradient(135deg, #f8fafc 0%, #ffffff 100%);
+    background: linear-gradient(135deg, #f9fafb 0%, #ffffff 100%);
     color: var(--text-color);
-    padding: 6rem 0;
-    min-height: 80vh;
+    padding: 5rem 0;
+    min-height: 75vh;
     display: flex;
     align-items: center;
     border-bottom: 1px solid #e5e7eb;
@@ -186,24 +192,27 @@ code {
 
 /* Enhanced Form Styles */
 .form-control, .form-select {
-    border-radius: var(--border-radius-sm);
-    border: 2px solid #e2e8f0;
+    border-radius: 12px;
+    border: 2px solid #e5e7eb;
     transition: var(--transition);
-    padding: 0.875rem 1rem;
+    padding: 1rem 1.25rem;
     font-size: 1rem;
     background-color: #ffffff;
     color: var(--text-color);
+    box-shadow: 0 1px 3px rgba(0, 0, 0, 0.1);
 }
 
 .form-control:focus, .form-select:focus {
     border-color: var(--primary-color);
-    box-shadow: 0 0 0 3px rgba(99, 102, 241, 0.1);
+    box-shadow: 0 0 0 4px rgba(79, 70, 229, 0.1);
     outline: none;
     background-color: #ffffff;
+    transform: translateY(-1px);
 }
 
 .form-control:hover, .form-select:hover {
-    border-color: #cbd5e1;
+    border-color: var(--primary-light);
+    box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
 }
 
 .form-label {