Loading video...
Video Failed to Load
๐ I built an AI NBA ๐ 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 โข 2 years ago โขvia X (Twitter)
10 Comments

๐ฅน

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.

Only thing missing is excitement and "from deep"

Yes!

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

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

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

Itโs hard to get the timing right but ideally they would talk a little faster

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

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.
