From 4e4c50045af658891d61ba528eabb4819643859f Mon Sep 17 00:00:00 2001 From: diodiogod <160325160+diodiogod@users.noreply.github.com> Date: Wed, 11 Feb 2026 23:45:02 -0300 Subject: [PATCH] docs: fix emoji encoding and update IndexTTS-2 size - Fix: Insert Zero Width Non-Joiner between flag emojis in tables to prevent ligatures - Update: Set IndexTTS-2 model size to ~4.7GB in YAML and Tables --- README.md | 18 ++++++++--------- docs/Dev reports/tts_audio_suite_engines.yaml | 2 +- docs/ENGINE_COMPARISON.md | 20 +++++++++---------- scripts/generate_engine_tables.py | 19 +++++++++--------- 4 files changed, 29 insertions(+), 30 deletions(-) diff --git a/README.md b/README.md index 59d10042..0d3bde7a 100644 --- a/README.md +++ b/README.md @@ -25,21 +25,19 @@ A comprehensive ComfyUI extension providing unified Text-to-Speech, Voice Conver | Engine | Languages | Size | Key Features | |--------|-----------|------|--------------| -| **F5-TTS** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต +4 | ~1.2GB each | Targeted Word/Speech Editing, Speed control | -| **ChatterBox** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท +4 | ~4.3GB | Expressiveness slider | +| **F5-TTS** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ต +4 | ~1.2GB each | Targeted Word/Speech Editing, Speed control | +| **ChatterBox** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ท +4 | ~4.3GB | Expressiveness slider | | **ChatterBox 23L** | ๐ŸŒ 24 languages | ~4.3GB | 24 languages in single model, emotion tokens (v2 - doesn't work) | -| **VibeVoice** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๏ฟฝ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๏ฟฝ๐Ÿ‡ฎ๏ฟฝ +21 | 5.4GB / 18GB | 90-min long-form, Native 4-speaker (Base models) | -| **Higgs Audio 2** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ฐ๐Ÿ‡ท | ~9GB | 3 multi-speaker, CUDA graphs (55+ tokens/sec) | -| **IndexTTS-2** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฏ๐Ÿ‡ต | ? | Emotion Control: 8 vectors, Text as reference | -| **CosyVoice3** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท | ~5.4GB | Paralinguistic tags | -| **Qwen3-TTS** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น +4 | ~3-6GB | Voice design, ASR (Automatic Speech Recognition) | -| **Step Audio EditX** | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท | ~7GB | Second Pass Speech Editing Node: 14 emotions, 32 speaking styles | +| **VibeVoice** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡น +21 | 5.4GB / 18GB | 90-min long-form, Native 4-speaker (Base models) | +| **Higgs Audio 2** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ฐ๐Ÿ‡ท | ~9GB | 3 multi-speaker, CUDA graphs (55+ tokens/sec) | +| **IndexTTS-2** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฏ๐Ÿ‡ต | ~4.7GB | Emotion Control: 8 vectors, Text as reference | +| **CosyVoice3** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ท | ~5.4GB | Paralinguistic tags | +| **Qwen3-TTS** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡น +4 | ~3-6GB | Voice design, ASR (Automatic Speech Recognition) | +| **Step Audio EditX** | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ท | ~7GB | Second Pass Speech Editing Node: 14 emotions, 32 speaking styles | | **RVC** | ๐ŸŒ Any | 100-300MB | Real-time VC, Pitch shift (ยฑ14) | - ๐Ÿ“Š **[Full comparison tables โ†’](docs/ENGINE_COMPARISON.md)** | **[Language matrix โ†’](docs/LANGUAGE_SUPPORT.md)** | **[Feature matrix โ†’](docs/FEATURE_COMPARISON.md)** -*Note: These tables are generated automatically from source: [tts_audio_suite_engines.yaml](docs/Dev%20reports/tts_audio_suite_engines.yaml)* ## ๐Ÿš€ Project Evolution Timeline diff --git a/docs/Dev reports/tts_audio_suite_engines.yaml b/docs/Dev reports/tts_audio_suite_engines.yaml index a07c468a..7ceafde1 100644 --- a/docs/Dev reports/tts_audio_suite_engines.yaml +++ b/docs/Dev reports/tts_audio_suite_engines.yaml @@ -281,7 +281,7 @@ engines: - id: indextts-2 name: IndexTTS-2 models: "IndexTTS-2" - size: "?" + size: "~4.7GB" capabilities: tts: true diff --git a/docs/ENGINE_COMPARISON.md b/docs/ENGINE_COMPARISON.md index 374ab9e1..34c179da 100644 --- a/docs/ENGINE_COMPARISON.md +++ b/docs/ENGINE_COMPARISON.md @@ -4,13 +4,13 @@ | Engine | Models | Size | TTS | SRT | VC | ASR | Special Features | Languages | | ------------------ | ----------------------------------------- | ------------ | --- | --- | --- | --- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- | -| **F5-TTS** | Base, v1, E2TTS + 8 lang models | ~1.2GB each | โœ… | โœ… | โŒ | โŒ | Targeted Word/Speech Editing, Speed control | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ง๐Ÿ‡ท๐Ÿ‡ต๐Ÿ‡ฑ๐Ÿ‡ฎ๐Ÿ‡ณ๐Ÿ‡น๐Ÿ‡ญ | -| **ChatterBox** | EN, DEร—3, IT, FR, RU, HY, KA, JA, KO, NO | ~4.3GB | โœ… | โœ… | โœ… | โŒ | Expressiveness slider | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท๐Ÿ‡ท๐Ÿ‡บ๐Ÿ‡ณ๐Ÿ‡ด๐Ÿ‡ฆ๐Ÿ‡ฒ๐Ÿ‡ฌ๐Ÿ‡ช | -| **ChatterBox 23L** | v1, v2, Vietnamese (Viterbox) | ~4.3GB | โœ… | โœ… | โœ… | โŒ | 24 languages in single model, emotion tokens (v2 - doesn't work) | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท๐Ÿ‡ท๐Ÿ‡บ๐Ÿ‡ต๐Ÿ‡น๐Ÿ‡ต๐Ÿ‡ฑ๐Ÿ‡ฎ๐Ÿ‡ณ๐Ÿ‡ฆ๐Ÿ‡ช๐Ÿ‡น๐Ÿ‡ท๐Ÿ‡น๐Ÿ‡ญ๐Ÿ‡ณ๐Ÿ‡ด๐Ÿ‡ป๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ฐ๐Ÿ‡ซ๐Ÿ‡ฎ๐Ÿ‡ฌ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡ฑ๐Ÿ‡ฒ๐Ÿ‡พ๐Ÿ‡ณ๐Ÿ‡ฑ๐Ÿ‡ธ๐Ÿ‡ช๐Ÿ‡ฐ๐Ÿ‡ช(+9) | -| **VibeVoice** | 1.5B, 7B, KugelAudio-0 (7B), Hindi-1.5B/7B | 5.4GB / 18GB | โœ… | โœ… | โŒ | โŒ | 90-min long-form, Native 4-speaker (Base models), Multilingual (KugelAudio), 4-bit quantization | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท๐Ÿ‡ท๐Ÿ‡บ๐Ÿ‡ง๐Ÿ‡ท๐Ÿ‡ต๐Ÿ‡ฑ๐Ÿ‡ฎ๐Ÿ‡ณ๐Ÿ‡ฆ๐Ÿ‡ช๐Ÿ‡น๐Ÿ‡ท๐Ÿ‡น๐Ÿ‡ญ๐Ÿ‡ณ๐Ÿ‡ด๐Ÿ‡ป๐Ÿ‡ณ๐Ÿ‡ฆ๐Ÿ‡ฒ๐Ÿ‡ฌ๐Ÿ‡ช๐Ÿ‡ฉ๐Ÿ‡ฐ๐Ÿ‡ซ๐Ÿ‡ฎ๐Ÿ‡ฌ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡ฑ๐Ÿ‡ฒ๐Ÿ‡พ๐Ÿ‡ณ๐Ÿ‡ฑ๐Ÿ‡ธ๐Ÿ‡ช๐Ÿ‡ฐ๐Ÿ‡ช | -| **Higgs Audio 2** | 3B | ~9GB | โœ… | โœ… | โŒ | โŒ | 3 multi-speaker, CUDA graphs (55+ tokens/sec) | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ฐ๐Ÿ‡ท | -| **IndexTTS-2** | IndexTTS-2 | ? | โœ… | โœ… | โŒ | โŒ | Emotion Control: 8 vectors, Text as reference, Audio as reference | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฏ๐Ÿ‡ต | -| **CosyVoice3** | 0.5B, 0.5B-RL | ~5.4GB | โœ… | โœ… | โœ… | โŒ | Paralinguistic tags | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท | -| **Qwen3-TTS** | 0.6B, 1.7B (CustomVoice/VoiceDesign/Base) | ~3-6GB | โœ… | โœ… | โŒ | โœ… | Voice design, ASR (Automatic Speech Recognition) | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท๐Ÿ‡ท๐Ÿ‡บ๐Ÿ‡ต๐Ÿ‡น | -| **Step Audio EditX** | 3B LLM + CosyVoice | ~7GB | โœ… | โœ… | โŒ | โŒ | Second Pass Speech Editing Node: 14 emotions, 32 speaking styles, Paralinguistic effects | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท | -| **RVC** | Community .pth | 100-300MB | โŒ | โŒ | โœ… | โŒ | Real-time VC, Pitch shift (ยฑ14), 6 HuBERT models, Language-independent | ๐Ÿ‡บ๐Ÿ‡ธ๐Ÿ‡จ๐Ÿ‡ณ๐Ÿ‡ฉ๐Ÿ‡ช๐Ÿ‡ช๐Ÿ‡ธ๐Ÿ‡ซ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡น๐Ÿ‡ฏ๐Ÿ‡ต๐Ÿ‡ฐ๐Ÿ‡ท๐Ÿ‡ท๐Ÿ‡บ๐Ÿ‡ง๐Ÿ‡ท๐Ÿ‡ต๐Ÿ‡ฑ๐Ÿ‡ฎ๐Ÿ‡ณ๐Ÿ‡ฆ๐Ÿ‡ช๐Ÿ‡น๐Ÿ‡ท๐Ÿ‡น๐Ÿ‡ญ๐Ÿ‡ณ๐Ÿ‡ด๐Ÿ‡ป๐Ÿ‡ณ๐Ÿ‡ฆ๐Ÿ‡ฒ๐Ÿ‡ฌ๐Ÿ‡ช๐Ÿ‡ฉ๐Ÿ‡ฐ๐Ÿ‡ซ๐Ÿ‡ฎ๐Ÿ‡ฌ๐Ÿ‡ท๐Ÿ‡ฎ๐Ÿ‡ฑ๐Ÿ‡ฒ๐Ÿ‡พ๐Ÿ‡ณ๐Ÿ‡ฑ๐Ÿ‡ธ๐Ÿ‡ช๐Ÿ‡ฐ๐Ÿ‡ช | \ No newline at end of file +| **F5-TTS** | Base, v1, E2TTS + 8 lang models | ~1.2GB each | โœ… | โœ… | โŒ | โŒ | Targeted Word/Speech Editing, Speed control | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ง๐Ÿ‡ทโ€‹๐Ÿ‡ต๐Ÿ‡ฑโ€‹๐Ÿ‡ฎ๐Ÿ‡ณโ€‹๐Ÿ‡น๐Ÿ‡ญ | +| **ChatterBox** | EN, DEร—3, IT, FR, RU, HY, KA, JA, KO, NO | ~4.3GB | โœ… | โœ… | โœ… | โŒ | Expressiveness slider | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ทโ€‹๐Ÿ‡ท๐Ÿ‡บโ€‹๐Ÿ‡ณ๐Ÿ‡ดโ€‹๐Ÿ‡ฆ๐Ÿ‡ฒโ€‹๐Ÿ‡ฌ๐Ÿ‡ช | +| **ChatterBox 23L** | v1, v2, Vietnamese (Viterbox) | ~4.3GB | โœ… | โœ… | โœ… | โŒ | 24 languages in single model, emotion tokens (v2 - doesn't work) | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ทโ€‹๐Ÿ‡ท๐Ÿ‡บโ€‹๐Ÿ‡ต๐Ÿ‡นโ€‹๐Ÿ‡ต๐Ÿ‡ฑโ€‹๐Ÿ‡ฎ๐Ÿ‡ณโ€‹๐Ÿ‡ฆ๐Ÿ‡ชโ€‹๐Ÿ‡น๐Ÿ‡ทโ€‹๐Ÿ‡น๐Ÿ‡ญโ€‹๐Ÿ‡ณ๐Ÿ‡ดโ€‹๐Ÿ‡ป๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ฐโ€‹๐Ÿ‡ซ๐Ÿ‡ฎโ€‹๐Ÿ‡ฌ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡ฑโ€‹๐Ÿ‡ฒ๐Ÿ‡พโ€‹๐Ÿ‡ณ๐Ÿ‡ฑโ€‹๐Ÿ‡ธ๐Ÿ‡ชโ€‹๐Ÿ‡ฐ๐Ÿ‡ช(+9) | +| **VibeVoice** | 1.5B, 7B, KugelAudio-0 (7B), Hindi-1.5B/7B | 5.4GB / 18GB | โœ… | โœ… | โŒ | โŒ | 90-min long-form, Native 4-speaker (Base models), Multilingual (KugelAudio), 4-bit quantization | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ทโ€‹๐Ÿ‡ท๐Ÿ‡บโ€‹๐Ÿ‡ง๐Ÿ‡ทโ€‹๐Ÿ‡ต๐Ÿ‡ฑโ€‹๐Ÿ‡ฎ๐Ÿ‡ณโ€‹๐Ÿ‡ฆ๐Ÿ‡ชโ€‹๐Ÿ‡น๐Ÿ‡ทโ€‹๐Ÿ‡น๐Ÿ‡ญโ€‹๐Ÿ‡ณ๐Ÿ‡ดโ€‹๐Ÿ‡ป๐Ÿ‡ณโ€‹๐Ÿ‡ฆ๐Ÿ‡ฒโ€‹๐Ÿ‡ฌ๐Ÿ‡ชโ€‹๐Ÿ‡ฉ๐Ÿ‡ฐโ€‹๐Ÿ‡ซ๐Ÿ‡ฎโ€‹๐Ÿ‡ฌ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡ฑโ€‹๐Ÿ‡ฒ๐Ÿ‡พโ€‹๐Ÿ‡ณ๐Ÿ‡ฑโ€‹๐Ÿ‡ธ๐Ÿ‡ชโ€‹๐Ÿ‡ฐ๐Ÿ‡ช | +| **Higgs Audio 2** | 3B | ~9GB | โœ… | โœ… | โŒ | โŒ | 3 multi-speaker, CUDA graphs (55+ tokens/sec) | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ฐ๐Ÿ‡ท | +| **IndexTTS-2** | IndexTTS-2 | ~4.7GB | โœ… | โœ… | โŒ | โŒ | Emotion Control: 8 vectors, Text as reference, Audio as reference | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฏ๐Ÿ‡ต | +| **CosyVoice3** | 0.5B, 0.5B-RL | ~5.4GB | โœ… | โœ… | โœ… | โŒ | Paralinguistic tags | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ท | +| **Qwen3-TTS** | 0.6B, 1.7B (CustomVoice/VoiceDesign/Base) | ~3-6GB | โœ… | โœ… | โŒ | โœ… | Voice design, ASR (Automatic Speech Recognition) | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ทโ€‹๐Ÿ‡ท๐Ÿ‡บโ€‹๐Ÿ‡ต๐Ÿ‡น | +| **Step Audio EditX** | 3B LLM + CosyVoice | ~7GB | โœ… | โœ… | โŒ | โŒ | Second Pass Speech Editing Node: 14 emotions, 32 speaking styles, Paralinguistic effects | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ท | +| **RVC** | Community .pth | 100-300MB | โŒ | โŒ | โœ… | โŒ | Real-time VC, Pitch shift (ยฑ14), 6 HuBERT models, Language-independent | ๐Ÿ‡บ๐Ÿ‡ธโ€‹๐Ÿ‡จ๐Ÿ‡ณโ€‹๐Ÿ‡ฉ๐Ÿ‡ชโ€‹๐Ÿ‡ช๐Ÿ‡ธโ€‹๐Ÿ‡ซ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡นโ€‹๐Ÿ‡ฏ๐Ÿ‡ตโ€‹๐Ÿ‡ฐ๐Ÿ‡ทโ€‹๐Ÿ‡ท๐Ÿ‡บโ€‹๐Ÿ‡ง๐Ÿ‡ทโ€‹๐Ÿ‡ต๐Ÿ‡ฑโ€‹๐Ÿ‡ฎ๐Ÿ‡ณโ€‹๐Ÿ‡ฆ๐Ÿ‡ชโ€‹๐Ÿ‡น๐Ÿ‡ทโ€‹๐Ÿ‡น๐Ÿ‡ญโ€‹๐Ÿ‡ณ๐Ÿ‡ดโ€‹๐Ÿ‡ป๐Ÿ‡ณโ€‹๐Ÿ‡ฆ๐Ÿ‡ฒโ€‹๐Ÿ‡ฌ๐Ÿ‡ชโ€‹๐Ÿ‡ฉ๐Ÿ‡ฐโ€‹๐Ÿ‡ซ๐Ÿ‡ฎโ€‹๐Ÿ‡ฌ๐Ÿ‡ทโ€‹๐Ÿ‡ฎ๐Ÿ‡ฑโ€‹๐Ÿ‡ฒ๐Ÿ‡พโ€‹๐Ÿ‡ณ๐Ÿ‡ฑโ€‹๐Ÿ‡ธ๐Ÿ‡ชโ€‹๐Ÿ‡ฐ๐Ÿ‡ช | \ No newline at end of file diff --git a/scripts/generate_engine_tables.py b/scripts/generate_engine_tables.py index ddbc44d6..84d889df 100644 --- a/scripts/generate_engine_tables.py +++ b/scripts/generate_engine_tables.py @@ -48,12 +48,13 @@ def generate_engine_comparison(data): output.append("") output.append("## Engine Comparison") output.append("") - output.append("| Engine | Models | Size | TTS | SRT | VC | ASR | Special Features | Languages |") - output.append("| ------------------ | ----------------------------------------- | ------------ | --- | --- | --- | --- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |") + output.append("| Engine | Models | Size | TTS | SRT | VC | ASR | Special Features | Languages |") + output.append("| ------------------ | ----------------------------------------- | ------------ | --- | --- | --- | --- | ---------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------- |") for e in engines: # Extract flags from languages - flags = "".join( + # Use Zero Width Space to prevent flag ligature issues + flags = "\u200B".join( lang_data["flag"] for lang_data in e["languages"].values() if lang_data["supported"] @@ -72,11 +73,11 @@ def generate_engine_comparison(data): e["size"].ljust(12), format_support(e["capabilities"]["tts"]), format_support(e["capabilities"]["srt"]), - format_support(e["capabilities"]["vc"]), - format_support(e["capabilities"]["asr"]), - features.ljust(88), - flags.ljust(88) - ] + format_support(e["capabilities"]["vc"]), + format_support(e["capabilities"]["asr"]), + features.ljust(88), + flags.ljust(88) + ] output.append("| " + " | ".join(row) + " |") @@ -106,7 +107,7 @@ def generate_readme_condensed_table(data): if count >= 6: # Limit to 6 flags for readability break - lang_display = "".join(flags) + lang_display = "\u200B".join(flags) # Special handling for ChatterBox 23L if e["id"] == "chatterbox-23l":