polaris-audio/polaris-tts-lite

Overview

A light text-to-speech voice that renders faster than real time on a CPU.

polaris-audio/polaris-tts-lite is a 80M-parameter text to speech model, published in onnx under the cc-by-4.0 license.

Intended use

• Text to speech in en.
• Research, prototypes and products that keep a person in the loop.
• Fine-tuning as a starting point for a narrower task.

How to use

# Command-line client (planned; the shape may change)
pace pull polaris-audio/polaris-tts-lite

# Python (planned)
from openpace import load
model = load("polaris-audio/polaris-tts-lite")

Limitations

• Heavy accents, overlapping speakers and very noisy audio lower accuracy.
• Never use a synthetic voice to impersonate a real person.

License

Released under cc-by-4.0. Read the license file before using the weights commercially.