MeloTTS-ES: Optimized for Qualcomm Devices
MeloTTS is a high-quality multi-lingual text-to-speech library for English, Chinese and Spanish language.
This is based on the implementation of MeloTTS-ES found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Deploying MeloTTS-ES on-device
This model is compatible with the Qualcomm Voice AI SDK. Download the SDK from the Qualcomm Package Manager to deploy this model on-device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| VOICE_AI | mixed_with_float | Snapdragon® X2 Elite | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Snapdragon® X Elite | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Qualcomm® SA8775P | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Qualcomm® SA7255P | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | Download |
| VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit MeloTTS-ES on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for MeloTTS-ES on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.audio_generation
Model Stats:
- Max decoded sequence length: 512 tokens
- Model checkpoint: myshell-ai/MeloTTS-Spanish
- Model size (decoder) (float): 55.5 MB
- Model size (encoder) (float): 32.0 MB
- Model size (flow) (float): 76.9 MB
- Model size (t5_decoder) (float): 21.8 MB
- Model size (t5_encoder) (float): 57.5 MB
- Number of parameters (decoder): 14.5M
- Number of parameters (encoder): 8.36M
- Number of parameters (flow): 20.1M
- Number of parameters (t5_decoder): 5.72M
- Number of parameters (t5_encoder): 15.1M
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| decoder | VOICE_AI | mixed_with_float | Snapdragon® X2 Elite | 40.808 ms | 1 - 1 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Snapdragon® X Elite | 82.732 ms | 1 - 1 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Gen 3 Mobile | 60.733 ms | 0 - 7 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 74.265 ms | 0 - 2 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 134.673 ms | 0 - 10 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 85.978 ms | 0 - 2 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® SA8775P | 83.846 ms | 0 - 10 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® SA8650P | 83.846 ms | 0 - 10 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® SA8255P | 83.846 ms | 0 - 10 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-9075 | 82.78 ms | 0 - 2 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-X7181 | 82.732 ms | 1 - 1 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ Q-8750 | 48.338 ms | 0 - 13 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Qualcomm® SA7255P | 134.673 ms | 0 - 10 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Mobile | 48.338 ms | 0 - 13 MB | NPU |
| decoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Gen 5 Mobile | 42.495 ms | 0 - 10 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Snapdragon® X2 Elite | 24.866 ms | 4 - 4 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Snapdragon® X Elite | 40.589 ms | 4 - 4 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Gen 3 Mobile | 30.505 ms | 4 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 39.107 ms | 4 - 10 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 66.642 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 41.735 ms | 4 - 5 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® SA8775P | 43.376 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® SA8650P | 43.376 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® SA8255P | 43.376 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-9075 | 42.814 ms | 4 - 9 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-X7181 | 40.589 ms | 4 - 4 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ Q-8750 | 25.272 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Qualcomm® SA7255P | 66.642 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Mobile | 25.272 ms | 2 - 11 MB | NPU |
| encoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Gen 5 Mobile | 23.828 ms | 2 - 10 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Snapdragon® X2 Elite | 67.288 ms | 2 - 2 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Snapdragon® X Elite | 128.874 ms | 2 - 2 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Snapdragon® 8 Gen 3 Mobile | 99.477 ms | 4 - 12 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 122.33 ms | 2 - 6 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 245.537 ms | 2 - 11 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 130.928 ms | 3 - 4 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® SA8775P | 128.72 ms | 2 - 12 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® SA8650P | 128.72 ms | 2 - 12 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® SA8255P | 128.72 ms | 2 - 12 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-9075 | 155.149 ms | 1 - 5 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-X7181 | 128.874 ms | 2 - 2 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ Q-8750 | 81.965 ms | 2 - 15 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Qualcomm® SA7255P | 245.537 ms | 2 - 11 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Mobile | 81.965 ms | 2 - 15 MB | NPU |
| flow | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Gen 5 Mobile | 71.031 ms | 2 - 11 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Snapdragon® X2 Elite | 0.339 ms | 1 - 1 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Snapdragon® X Elite | 0.416 ms | 1 - 1 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Gen 3 Mobile | 0.316 ms | 0 - 8 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 0.573 ms | 1 - 3 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 0.992 ms | 0 - 9 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.395 ms | 0 - 2 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® SA8775P | 0.651 ms | 0 - 10 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® SA8650P | 0.651 ms | 0 - 10 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® SA8255P | 0.651 ms | 0 - 10 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-9075 | 0.512 ms | 3 - 5 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-X7181 | 0.416 ms | 1 - 1 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ Q-8750 | 0.279 ms | 0 - 13 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Qualcomm® SA7255P | 0.992 ms | 0 - 9 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Mobile | 0.279 ms | 0 - 13 MB | NPU |
| t5_decoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Gen 5 Mobile | 0.287 ms | 0 - 11 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Snapdragon® X2 Elite | 0.64 ms | 0 - 0 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Snapdragon® X Elite | 1.05 ms | 0 - 0 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Gen 3 Mobile | 0.632 ms | 0 - 7 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 1.089 ms | 0 - 2 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-8275 | 2.839 ms | 0 - 9 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.904 ms | 0 - 1 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® SA8775P | 1.265 ms | 0 - 10 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® SA8650P | 1.265 ms | 0 - 10 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® SA8255P | 1.265 ms | 0 - 10 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-9075 | 1.142 ms | 0 - 2 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ IQ-X7181 | 1.05 ms | 0 - 0 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® Dragonwing™ Q-8750 | 0.525 ms | 0 - 13 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Qualcomm® SA7255P | 2.839 ms | 0 - 9 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Mobile | 0.525 ms | 0 - 13 MB | NPU |
| t5_encoder | VOICE_AI | mixed_with_float | Snapdragon® 8 Elite Gen 5 Mobile | 0.489 ms | 0 - 8 MB | NPU |
License
- The license for the original implementation of MeloTTS-ES can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
