Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
nostrebored
3 months ago
|
parent
|
context
|
favorite
| on:
Launch HN: RunAnywhere (YC W26) – Faster AI Infere...
It’s the TTS layer that is weird. I’m in the same boat — speech out is just a much worse modality than text when possible.
sanchitmonga22
3 months ago
[–]
Agreed for a lot of use cases. RCLI supports text-only mode (--no-speak flag or just type in the TUI instead of using push-to-talk). TTS makes sense for hands-free / eyes-free scenarios, but we dont force it.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
