Same here from South Africa and worse part we already had an ongoing use case -where we used the stss, inference and tts models to achieve our goal.
With the realtime api - we’ll make a single call and highly reduce latency.
Same here from South Africa and worse part we already had an ongoing use case -where we used the stss, inference and tts models to achieve our goal.
With the realtime api - we’ll make a single call and highly reduce latency.