Pocket TTS
MIT (code) · CC-BY-4.0 (weights)CPU speech generation, streaming, and voice cloning in a small model.
CPU speech generation, streaming, and voice cloning in a small model. Voice files have their own terms. Model downloads can require accepting Hugging Face access conditions.
Hear Pocket TTS
Pocket TTS · English 2026-01 checkpoint · Alba · local CPU · Same three scripts across the directory.
Best for: CPU speech generation, streaming, and voice cloning in a small model.
Before you choose: Voice files have their own terms. Model downloads can require accepting Hugging Face access conditions.
No comparable hardware benchmark verified. Check the official setup for your device.
Details reviewed 2026-09-14. Hardware figures are estimates unless a benchmark is linked.
Compare with similar
Compare all →Choose an alternative to hear both models together.
Voices
1 voiceThe scripts
Run Pocket TTS
pip install pocket-tts
pocket-tts generate --text "Hello from OpenSpeech."Sources & setup details
Pocket TTS FAQ
Do I need a GPU to run Pocket TTS?
Pocket TTS supports CPU inference. Speed depends on your processor, runtime, and text.
Can Pocket TTS clone voices?
Yes — Pocket TTS supports voice cloning from reference audio.
What license is Pocket TTS released under?
Pocket TTS is released under the MIT (code) · CC-BY-4.0 (weights) license. Always check the repository for the exact terms — some models license code and weights separately.
What languages does Pocket TTS support?
Pocket TTS supports English, French, German, Portuguese, Italian, Spanish.
Is there a hosted Pocket TTS API?
OpenSpeech Cloud is accepting production-access interest for Pocket TTS, but this model is not hosted in the beta. Use the official repository for current deployment options.