StarZero All shows Try the podcast clipper →

speech-to-text model

1 statements across 1 episodes · 0 bullish · 0 bearish · 1 people on the record · first statement Apr 14, 2026 by Mati Staniszewski · across every show →

Everything said about speech-to-text model, oldest first

Apr 14, 2026
Disclosure
ElevenLabs built internal speech-to-text models after market options fell short
“So speech-to-text model, Initially it was a model we did for ourselves because the models on the market just weren't good to annotate that data.”
Mati Staniszewski Apr 14, 2026 ▶ 7:16 The world of voice AI, with Mati Staniszewski of ElevenLabs
Made with StarZero

Turn any episode into a week of clips.

This entire site, about 28 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more