🎯 Major Feature Release: Intelligent Text Chunking
🚀 New Features
📏 Smart Text Chunking System
- 3-tier chunking strategy for optimal quality:
- Under 25s: No chunking (optimal quality)
- 25-40s: Gentle chunking at natural boundaries
- Over 40s: Aggressive but intelligent chunking
- Respects natural language boundaries: paragraphs, sentences, clauses
- Seamless audio concatenation using ffmpeg
- Voice cloning consistency across chunks
- Production-ready error handling and cleanup
🎵 What This Enables
Before v1.1.0:
- ❌ Long texts failed or produced poor quality
- ❌ Users had to manually split text
- ❌ Inconsistent results with long content
After v1.1.0:
- ✅ Any length text works automatically
- ✅ Professional quality maintained
- ✅ Seamless user experience
- ✅ Production-grade reliability
🔧 Technical Implementation
- Duration estimation: ~12 characters per second
- Intelligent break points: Paragraphs → Sentences → Clauses → Words
- Audio concatenation: Professional ffmpeg integration
- Memory efficient: Sequential chunk processing
- Configurable thresholds: Easy to adjust for different use cases
🐳 Docker Images
# Latest with chunking
docker pull tsavo/chatterbox-tts-api:latest
docker pull tsavo/chatterbox-tts-api:v1.1.0
docker pull tsavo/chatterbox-tts-api:v1.1
docker pull tsavo/chatterbox-tts-api:v1📖 Usage Examples
Long Text Processing (Now Supported!)
import requests
# This now works seamlessly with any length text!
long_text = """Your very long text here...
Multiple paragraphs...
Complex sentences...
All handled automatically!"""
response = requests.post("http://localhost:8000/tts", json={
"text": long_text,
"output_format": "mp3"
})
# Get your MP3 file - chunking handled transparently!
with open("output.mp3", "wb") as f:
f.write(response.content)🎯 Breaking Changes
- None! Fully backward compatible
- Existing API calls work exactly the same
- Chunking is transparent to users
🔄 Migration
- No migration needed
- Simply update to v1.1.0
- Long texts that previously failed now work automatically
This release transforms Chatterbox TTS from a demo tool into a production-ready service capable of handling real-world text processing needs! 🚀