正在加载视频...

视频加载失败

👀 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 次观看 • 2 年前 •via X (Twitter)

10 条评论

Alex Ker 🔭 的头像
Alex Ker 🔭2 年前

🥹

Alex Ker 🔭 的头像
Alex Ker 🔭2 年前

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 🇺🇸 的头像
🇺🇸TERRENCE 🇺🇸2 年前

Only thing missing is excitement and "from deep"

Alex Ker 🔭 的头像
Alex Ker 🔭2 年前

Yes!

Justin Halford 的头像
Justin Halford2 年前

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

Alex Ker 🔭 的头像
Alex Ker 🔭2 年前

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

chance 的头像
chance2 年前

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

Alex Ker 🔭 的头像
Alex Ker 🔭2 年前

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

jeffw 的头像
jeffw2 年前

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

Alex Ker 🔭 的头像
Alex Ker 🔭2 年前

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.

相关视频