PiperTTS-EN-Amy
High‑quality text‑to‑speech for English (Amy voice).
PiperTTS is a high‑quality multi‑lingual text‑to‑speech library. This model uses the Amy English voice (medium quality). Its training data is licensed CC‑BY‑SA‑4.0 per the mimic3‑voices project (https://github.com/MycroftAI/mimic3‑voices).
Not supported
This model is currently not supported on any Compute chipset.
To see performance metrics for this model on other chipsets, click the button below.
View for other chipsetsTechnical Details
Max decoded sequence length:64 tokens
Model checkpoint:rhasspy/piper-checkpoints (en_US/amy/medium)
Model size (charsiu_decoder) (float):21.9 MB
Model size (charsiu_encoder) (float):57.7 MB
Model size (decoder) (float):6.43 MB
Model size (encoder) (float):28.9 MB
Model size (flow) (float):28.4 MB
Model size (sdp) (float):2.50 MB
Applicable Scenarios
- Smart Home
- Accessibility
License
Model:MIT
Tags
- real-time
Supported Compute Devices
- Snapdragon X Elite CRD
- Snapdragon X Plus 8-Core CRD
- Snapdragon X2 Elite CRD
Supported Compute Chipsets
- Snapdragon® X Elite
- Snapdragon® X Plus 8-Core
- Snapdragon® X2 Elite
Related Models
See all models
Looking for more? See models created by industry leaders.
Discover Model Makers