PocketTTS

Lightweight CPU-first speech

Runtime

CPU-first

License

CC BY 4.0

Python

3.10-3.14

OpenVox fit

Lightweight local

Model overview

Built into OpenVox for private local voice generation.

Hugging Face

Pocket TTS is a lightweight text-to-speech model designed to run efficiently on CPUs without GPU infrastructure or web APIs.

Pocket TTS is a lightweight TTS application designed to run efficiently on CPUs.

It does not require the GPU version of PyTorch and supports modern Python versions.

OpenVox positions PocketTTS for lightweight systems, streaming, and local generation where CPU practicality matters.

OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.

Source: kyutai/pocket-tts.