Загрузка видео...

Не удалось загрузить видео

На главную

👀 I built an AI NBA 🏀 commentator using OpenAI Vision API + TTS magic in 15min. Clip taken from when Damian Lillard ended PG's career with the game winner in 2019. Same pipeline can be applied for any highlights and buzzerbeaters.

223,614 просмотров • 2 лет назад •via X (Twitter)

Комментарии: 10

Фото профиля Alex Ker 🔭
Alex Ker 🔭2 лет назад

🥹

Фото профиля Alex Ker 🔭
Alex Ker 🔭2 лет назад

My heart is full:) If you enjoyed this, follow @thealexker for more on applied AI, startups, and project insights and let's learn together. High-signal content only, no fluff.

Фото профиля 🇺🇸TERRENCE 🇺🇸
🇺🇸TERRENCE 🇺🇸2 лет назад

Only thing missing is excitement and "from deep"

Фото профиля Alex Ker 🔭
Alex Ker 🔭2 лет назад

Yes!

Фото профиля Justin Halford
Justin Halford2 лет назад

With proper intonation and a little bit cleaner choice of phrasing, this is a killer product! Great job 🔥

Фото профиля Alex Ker 🔭
Alex Ker 🔭2 лет назад

Thanks Justin! I’m just surprised the default text to voice is already so natural albeit a bit emotionless

Фото профиля chance
chance2 лет назад

Would be even cooler to delay video by a couple frames so the commentator can prepare with enthusiasm

Фото профиля Alex Ker 🔭
Alex Ker 🔭2 лет назад

It’s hard to get the timing right but ideally they would talk a little faster

Фото профиля jeffw
jeffw2 лет назад

Honestly SO good! Dagger. 🗡️ No trouble with gpt-4-vision rate limits?

Фото профиля Alex Ker 🔭
Alex Ker 🔭2 лет назад

fixing the rate limit is most of the work haha. at 30fps I sample every 150frames or every 5 seconds to get around it. also the video is short so there isn't a lot of output tokens. the limit is 10k/min atm.

Похожие видео