- Created comprehensive YAML source of truth for all TTS engines - Implemented Python generator for 3 documentation tables: * ENGINE_COMPARISON.md - Main engine overview with capabilities * LANGUAGE_SUPPORT.md - Detailed language support matrix * FEATURE_COMPARISON.md - Feature capabilities comparison - YAML captures all engine metadata without information loss - Tables auto-generated via scripts/generate_engine_tables.py - Added flag emojis to language support table for easy scanning - Speed performance fixes: F5-TTS marked as "Very Fast"
1.2 KiB
1.2 KiB
Feature Comparison Matrix
Feature Comparison Matrix
| Feature | F5-TTS | ChatterBox | ChatterBox 23L | VibeVoice | Higgs Audio 2 | IndexTTS-2 | CosyVoice3 | Qwen3-TTS | Step Audio EditX | RVC |
|---|---|---|---|---|---|---|---|---|---|---|
| Voice Cloning | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ (Base model) | ✅ | ⚠️ (needs training) |
| Native Multi-Speaker | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ |
| Voice Conversion | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ✅ |
| Emotion Control | ❌ | ❌ | ⚠️ (v2 tags - doesn't work) | ❌ | ⚠️ (via prompt) | ✅ (8 emotions) | ⚠️ (via instruct) | ⚠️ (via instruct) | ✅ (14 emotions) | ❌ |
| Native Long-form (90min) | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | N/A |
| Community Finetunes | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ✅ |
| VRAM Efficient | ✅ | ✅ | ✅ | ⚠️ (5-18GB) | ⚠️ (9GB) | ⚠️ (9-12GB) | ✅ (5.4GB) | ✅ (3-6GB) | ⚠️ (7GB) | ✅ |
| Speed/Performance | ✅ Very Fast | ✅ Fast | ✅ Fast | ⚠️ | ⚠️ | ⚠️ | ✅ Fast | ⚠️ | ⚠️ | ✅ Fast |