Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

👀 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.

223,642 görüntüleme • 2 yıl önce •via X (Twitter)

10 Yorum

Alex Ker 🔭 profil fotoğrafı
Alex Ker 🔭2 yıl önce

🥹

Alex Ker 🔭 profil fotoğrafı
Alex Ker 🔭2 yıl önce

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.

🇺🇸TERRENCE 🇺🇸 profil fotoğrafı
🇺🇸TERRENCE 🇺🇸2 yıl önce

Only thing missing is excitement and "from deep"

Alex Ker 🔭 profil fotoğrafı
Alex Ker 🔭2 yıl önce

Yes!

Justin Halford profil fotoğrafı
Justin Halford2 yıl önce

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

Alex Ker 🔭 profil fotoğrafı
Alex Ker 🔭2 yıl önce

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

chance profil fotoğrafı
chance2 yıl önce

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

Alex Ker 🔭 profil fotoğrafı
Alex Ker 🔭2 yıl önce

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

jeffw profil fotoğrafı
jeffw2 yıl önce

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

Alex Ker 🔭 profil fotoğrafı
Alex Ker 🔭2 yıl önce

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.

Benzer Videolar