Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Model reply
Good evening, you're listening to Night Shift on 98.4. I'm Mara, and tonight, we're taking your calls about the songs that got you through a long drive. Hi Mara, it's Theo, calling from a truck stop outside Tucson. I've been on the road since 5 this morning. Theo, welcome to the show. Which song kept you awake on that stretch? Honestly? An old soul record my dad used to play. Every time the chorus kicks in, I roll the window down and sing along. That's the best kind of answer. Drive safe out there, Theo. This next one is for you.
late-night-radio-call A 38-second host-and-caller call with word timestamps on; the two voices came back as speaker 0 and speaker 1 at the right turns.
- timestamps
- Model reply
Welcome to tonight's tasting. We begin with a young red from La Rioja: red fruit notes, a hint of vanilla, and a smooth finish. Next, we'll taste a white from Galicia: fresh and saline, perfect with seafood. Take notes, because at the end we'll vote for your favorite.
spanish-wine-tasting-to-english A 17-second Spanish narration with target_language set to English, returned as an English translation.
- en
- Model reply
Good evening, you're listening to Night Shift on 98.4. I'm Mara, and tonight, we're taking your calls about the songs that got you through a long drive. Hi Mara, it's Theo, calling from a truck stop outside Tucson. I've been on the road since 5 this morning. Theo, welcome to the show. Which song kept you awake on that stretch? Honestly, an old soul record my dad used to play. Every time the chorus kicks in, I roll the window down and sing along. That's the best kind of answer. Drive safe out there, Theo. This next one is for you.
radio-call-over-jazz The same call mixed over a loud jazz piano track, transcribed without any options; the text matches the clean recording.
This example starts at $0.00003 per second of input audio. The Playground updates the estimate when you change the settings.
