## 📊 To Test - https://github.com/neuphonic/neutts-air - https://huggingface.co/canopylabs/orpheus-3b-0.1-ft/tree/main - https://huggingface.co/openbmb/VoxCPM1.5 - https://huggingface.co/Zyphra/Zonos-v0.1-transformer - https://huggingface.co/kyutai/tts-0.75b-en-public - https://huggingface.co/kyutai/tts-1.6b-en_fr/tree/main - https://huggingface.co/FunAudioLLM/Fun-CosyVoice3-0.5B-2512 - https://huggingface.co/YatharthS/MiraTTS - https://huggingface.co/kyutai/pocket-tts - https://huggingface.co/OpenMOSS-Team/MOSS-TTS ### 🔄 Multimodal / Speech-to-Speech (ASR + TTS) - https://huggingface.co/stepfun-ai/Step-Audio-R1.1 - https://huggingface.co/LiquidAI/LFM2.5-Audio-1.5B ## ⭐ Exceptional ## ✅ Good - https://huggingface.co/microsoft/VibeVoice-1.5B - https://huggingface.co/nari-labs/Dia2-1B - https://huggingface.co/nari-labs/Dia2-2B - https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice - https://huggingface.co/ResembleAI/chatterbox-turbo (phonemes, fast, slightly lesser quality) ## ❌ Unacceptable - https://huggingface.co/microsoft/VibeVoice-Realtime-0.5B (requires much older transformers) - https://huggingface.co/fishaudio/s2-pro (good quality but very very heavy) - ~~https://huggingface.co/zai-org/GLM-TTS~~ (too difficult to use)
📊 To Test
🔄 Multimodal / Speech-to-Speech (ASR + TTS)
⭐ Exceptional
✅ Good
❌ Unacceptable
https://huggingface.co/zai-org/GLM-TTS(too difficult to use)