Pick a drill, speak for 30 to 90 seconds, and get scored on pacing, fluency, vocabulary and coherence. Every filler and long pause lands on a transcript you can read back. On an iPhone with Apple Intelligence it runs on the device, with no account.
Hi Product Hunt,
I built Orato after trying a handful of speech-coaching apps that all wanted to
upload my voice to a server I'd never heard of. I'd had a run of bad standups
and one interview I'd rather not describe, and paying a stranger's GPU to listen
to me ramble stopped making sense.
Apple Intelligence runs a language model on the phone itself, so I built the
version I wanted:
• Pick a drill: Impromptu, Defend a Topic, Three Questions, Tell a Story,
Elevator Pitch, Read Aloud
• Speak for 30 to 90 seconds
• Get scored on pacing, fluency, vocabulary and coherence
• Read the take back on a transcript with every filler tinted and every pause
timed
• Tap any line to see what the coach noticed at that moment
The privacy claim, in full, because you'd find this in Settings anyway. Your
audio recording never leaves the phone, on any path, under any setting. On an
iPhone with Apple Intelligence the whole pipeline is local: transcription,
scoring, coaching, no account, works on a plane. Two opt-in paths do send
transcript text off the device. One is a fallback for iPhones too old to run
Apple Intelligence. The other is a Pro toggle for a deeper report, and it ships
switched off. Both ask you to sign in first.
Free gives you three coached sessions a week and you spend them on whichever
drills you like. Pro lifts the limit. Monthly and yearly start with 7 days free.
Three things I'd like your read on:
• Which drill is missing. Sales pitch? Wedding speech?
• Whether the scoring reads as useful or as a horoscope
• What would keep this on your home screen past week one
I'm here all day and I'll answer everything, including the awkward ones.
Petros, solo dev, @OratoSpeaking
Report
It's kinda painful hearing yourself say "um" every five seconds once you actually listen back haha. But that's probably exactly why practicing like this can be so useful. Congrats on getting this out there! @petros_tepoyan1
On device with no account is the reason this can work. Nobody practises sounding bad in front of a server they don't trust, and the whole thing depends on people being willing to do a terrible first take. The scoring is where I'd be careful. Pacing and fluency are measurable, coherence is a judgement call, and if that one is wrong even once people quietly stop believing the other three.
Papaya
It's kinda painful hearing yourself say "um" every five seconds once you actually listen back haha. But that's probably exactly why practicing like this can be so useful. Congrats on getting this out there! @petros_tepoyan1
Humalike
Congrats on the launch :)))
On device with no account is the reason this can work. Nobody practises sounding bad in front of a server they don't trust, and the whole thing depends on people being willing to do a terrible first take. The scoring is where I'd be careful. Pacing and fluency are measurable, coherence is a judgement call, and if that one is wrong even once people quietly stop believing the other three.