Skip to main content

Posts

Featured

New ask Hacker News story: Why Fireworks doesn't support Voice AI

Why Fireworks doesn't support Voice AI 3 by kushalpatil07 | 0 comments on Hacker News. I started thinking over why doesn't fireworks support voice models. There are really good opensource models available now, like parakeet, kokoro, Qwen ASR etc but no way to use it without managing a bunch of GPUs yourself. Even LLMs like Gemma 4 used by voice agents are not supported. Then I figured that the inference platform needs to be optimized differently for the kind of usecase you are using. Lets take an example for LLMs, not even STT and TTS. - Coding agents -> lot of cached input, needs to optimize for KV cache - Creation slides/blogs -> lots of output, needs to optimize for speculative decoding - Voice LLMs -> Cached input small output, not yet figured out on how to optimize this. So TTS and STT is a completely different ballgame. What I don't know is the timing, do people want to use open source models like kokoro, parakeet, Qwen etc RIGHT NOW?

Latest Posts

New ask Hacker News story: Ask HN: What paid tools have you now replaced with personalized AI-coded tools?

New ask Hacker News story: The LLMs Problems

New ask Hacker News story: Ask HN: Does AI research need "world models" more than bigger LLMs?

New ask Hacker News story: Ask HN: Who is hiring? (August 2026)

New ask Hacker News story: Ask HN: Who is quitting? (August 2026)

New ask Hacker News story: What Is Decispher?

New ask Hacker News story: Ask HN: What are you working on? (August 2026)

New ask Hacker News story: Ask HN: When did we go from agentic loops to graphs?

New ask Hacker News story: Tell HN: I hate your fuzzy search

New ask Hacker News story: Ask HN: Give Me Your Earworm