Miso Labs · Text-to-Speech
MisoTTS 8B
8B-parameter RVQ-Transformer TTS with a Llama-3.2-style backbone + 300M audio decoder, using the Mimi codec with 32 codebooks and 2,048-token max length; English-only, ~24GB VRAM at bf16, ships with SilentCipher watermarking.
Open the source ↗Similar Audio & Speech releases
- AuK
SJTU, Tencent Hunyuan & Shanghai Innovation Institute · Unified Speech Editing · Week 37, 2026
- Faster Qwen3-TTS
andimarafioti · Text-to-Speech · Week 9, 2026
- Step-Audio-EditX
StepFun · Text-to-Speech · Week 46, 2025
- Stable Audio Open Small
Stability AI & ARM · Text-to-Speech · Week 19, 2025
- ARC Text-to-Audio Generation
UC San Diego, Stability AI, Arm · Text-to-Speech · Week 18, 2025
- Audio8-TTS-Realistic 0.6B
Audio8 (edge0-ai) · Compact multilingual TTS · Week 45, 2026
More from Miso Labs
- Miso-TTS
Miso Labs · Text-to-Speech · Week 24, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.