@AlphaSignalAI: A 66M parameter model just beat ElevenLabs on a Raspberry Pi. Text-to-speech has lived in the cloud for years. Every sp…

X AI KOLs Timeline Models

Summary

Supertonic 3 is a 99M parameter open-source TTS model that runs entirely on-device, beating ElevenLabs on a Raspberry Pi with 167x faster than real-time performance on a laptop CPU.

A 66M parameter model just beat ElevenLabs on a Raspberry Pi. Text-to-speech has lived in the cloud for years. Every spoken character cost an API call and a fraction of a cent. Supertonic 3 is an open-source TTS model that runs entirely on the device. No network, no key, no per-character billing. The model is 99M parameters and ships as an ONNX file. It hits 167x faster than real-time on a laptop CPU. That works out to about 1,263 characters of speech per second. Larger open systems sit closer to 55 to 287. What the on-device design unlocks: > Runs offline on a Raspberry Pi > Works inside a browser tab > Handles phone numbers and currency > Reads dates without any preprocessing > Inline tags for laugh and breath Language coverage jumped from 5 to 31 in this release. The public interface stayed identical to the previous version.
Original Article
View Cached Full Text

Cached at: 05/22/26, 05:56 PM

A 66M parameter model just beat ElevenLabs on a Raspberry Pi.

Text-to-speech has lived in the cloud for years.

Every spoken character cost an API call and a fraction of a cent.

Supertonic 3 is an open-source TTS model that runs entirely on the device.

No network, no key, no per-character billing.

The model is 99M parameters and ships as an ONNX file.

It hits 167x faster than real-time on a laptop CPU.

That works out to about 1,263 characters of speech per second.

Larger open systems sit closer to 55 to 287.

What the on-device design unlocks:

Runs offline on a Raspberry Pi Works inside a browser tab Handles phone numbers and currency Reads dates without any preprocessing Inline tags for laugh and breath

Language coverage jumped from 5 to 31 in this release.

The public interface stayed identical to the previous version.

Similar Articles

@GoJun315: Open-source TTS that runs locally and beats ElevenLabs. Supertonic, a speech synthesis model that runs entirely on-device, no internet required, zero API costs. - Only 99M parameters, 167x faster than real-time on M4 Pro, runs on Raspberry Pi - Supports 31 languages, covering…

X AI KOLs Timeline

Supertonic is a lightning-fast, on-device TTS model with 99M parameters, supporting 31 languages. It runs locally with no API costs, outperforms cloud TTS on accuracy for numbers, phone numbers, and technical terms, and can be installed via Python, Node.js, Rust, Go, and more.