Loading video...

Video Failed to Load

Go Home

๐Ÿ‘€ I built an AI NBA ๐Ÿ€ 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 views โ€ข 2 years ago โ€ขvia X (Twitter)

10 Comments

Alex Ker ๐Ÿ”ญ's profile picture
Alex Ker ๐Ÿ”ญ2 years ago

๐Ÿฅน

Alex Ker ๐Ÿ”ญ's profile picture
Alex Ker ๐Ÿ”ญ2 years ago

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.

๐Ÿ‡บ๐Ÿ‡ธTERRENCE ๐Ÿ‡บ๐Ÿ‡ธ's profile picture
๐Ÿ‡บ๐Ÿ‡ธTERRENCE ๐Ÿ‡บ๐Ÿ‡ธ2 years ago

Only thing missing is excitement and "from deep"

Alex Ker ๐Ÿ”ญ's profile picture
Alex Ker ๐Ÿ”ญ2 years ago

Yes!

Justin Halford's profile picture
Justin Halford2 years ago

With proper intonation and a little bit cleaner choice of phrasing, this is a killer product! Great job ๐Ÿ”ฅ

Alex Ker ๐Ÿ”ญ's profile picture
Alex Ker ๐Ÿ”ญ2 years ago

Thanks Justin! Iโ€™m just surprised the default text to voice is already so natural albeit a bit emotionless

chance's profile picture
chance2 years ago

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

Alex Ker ๐Ÿ”ญ's profile picture
Alex Ker ๐Ÿ”ญ2 years ago

Itโ€™s hard to get the timing right but ideally they would talk a little faster

jeffw's profile picture
jeffw2 years ago

Honestly SO good! Dagger. ๐Ÿ—ก๏ธ No trouble with gpt-4-vision rate limits?

Alex Ker ๐Ÿ”ญ's profile picture
Alex Ker ๐Ÿ”ญ2 years ago

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.

Related Videos