Hey everyone! I’m still pretty new to all this, but I just finished putting together a small Flask app to show my team what Cartesia can actually do. We’ve been talking about voice AI for some customer support prototypes, and I wanted to move past the marketing slides and see it in action.
I kept it super simple: a single page with a text box where you type a prompt, and it streams back the audio response from Cartesia’s API. I used their Python SDK and the `requests` library to handle the streaming. The most interesting part was trying out different voices from their catalog—some felt really natural, others a bit robotic, but it was cool to compare.
Has anyone else built something similar? I’m wondering about a couple things:
- Did you run into issues with latency during the stream, especially on slower connections?
- How did you handle choosing a voice? I got a bit of “demo fatigue” clicking through all the options.
- For those using it in production-ish demos, any pitfalls with API costs piling up during testing?
I’m also curious if there’s a smarter way to manage trial credits or if people just set hard limits in their code.
New here!
Just my two cents.