roatienza/efficientspeech

PyTorch code implementation of EfficientSpeech - to be presented at ICASSP2023.

47
/ 100
Emerging

This project helps convert written text into natural-sounding speech audio files, directly on small, low-power devices like a Raspberry Pi. You provide the text you want spoken, and it generates a high-quality audio file (.wav) of that text. This is ideal for developers creating applications that need to deliver spoken content on embedded systems, mobile devices, or in resource-constrained environments.

180 stars. No commits in the last 6 months.

Use this if you need to integrate text-to-speech capabilities into an application running on a device with limited computational power and memory, where traditional TTS models are too slow or too large.

Not ideal if you primarily need extremely high-fidelity, human-like speech generation for professional voiceovers on powerful servers, or if you require support for many languages beyond English.

embedded-systems voice-user-interface speech-synthesis edge-computing device-software
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

180

Forks

36

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Mar 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/roatienza/efficientspeech"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.