Stream English speech locally with the compact 31M model.
- Released
- Oct 20, 2026
One input, different models. Compare outputs and measured speed side by side on your own device.
Model comparisons are coming with the upgraded LocalAI Tools. Explore the models below, or join the waitlist to hear when it’s ready.
Stream English speech locally with the compact 31M model.
Generate English speech in your browser from text and a reference recording. Returns 24 kHz audio.
Generate English speech from text and a reference voice. Verified WebGPU inference with complete24kHz audio.
Read English text aloud with a compact speech-synthesis model and preset voices. Returns 24 kHz mono audio; designed for short text inputs.
Read English text aloud using a speaker embedding to condition the voice. Returns 16 kHz mono audio; an optional speaker-embedding file must contain exactly 512 float32 values.
Turn short English text into spoken audio using a selected voice. Returns 24 kHz mono speech for narration, previews, and reading text aloud.
Synthesize short English text as 24 kHz speech in the built-in Dave voice.
Generate short English preset speech in the browser, with complete24kHz mono audio and incremental playback.