Polaris Audio Lab
Organization@polaris-audio
Speech in, speech out. Small recognisers and expressive voices.
speech recognitionspeech synthesis
3
Models
2
Datasets
2
Spaces
polaris-audio/polaris-asr-medium
Speech recognition with word-level timestamps, robust to background noise and phone-quality audio.
Speech recognition770MUpdated Sep 23, 2026
polaris-audio/polaris-tts-lite
A light text-to-speech voice that renders faster than real time on a CPU.
Text to speech80MUpdated Sep 16, 2026
polaris-audio/polaris-asr-tiny
A tiny recogniser for voice commands and short dictation on phones.
Speech recognition40MUpdated Sep 3, 2026