Hj HIMANSHU JAIN
← Back to portfolio
Case Study · Product I built

VoiceSkill

A trainer that captures how you actually speak and turns it into a reusable style profile — so the AI tools you use sound like you, not like generic AI.

Voice AIWhisperPersonalisationMulti-UserPM Tooling
RolePM + builder, end-to-end
StackNext.js · Groq Whisper · Supabase
StatusLive

01 The problem

Everyone who uses AI writing tools hits the same wall eventually: the output is competent but sounds nothing like them. It's flat, generic, over-polished — recognisably "AI." Fixing that by hand, every time, defeats the point of the tool.

The usual fix is to paste a few writing samples into a prompt. But most people express themselves more naturally by speaking than by curating written samples — and the way you talk carries your rhythm, your phrasing, your fillers, the texture that makes a voice yours.

The core idea

Capture voice through speech, not written samples. VoiceSkill records how you actually talk, transcribes it, and distils it into a reusable profile — a portable style guide you can hand to any AI tool so it writes in your voice from the start.

02 How it works

1 · Speak

Record naturally

You talk the way you normally would — the most honest signal of your actual voice.

2 · Transcribe

Groq Whisper

Speech turned to text accurately, preserving your real phrasing rather than cleaning it up.

3 · Distil

Style profile

The transcript analysed into a reusable voice profile — tone, rhythm, characteristic patterns.

4 · Reuse

Export & library

Export the profile as a portable spec; multiple users each keep their own in a profile library.

03 The design decisions

04 What I'd watch next

VoiceSkill is live but hasn't been validated with real users. The open questions:

This case study is written from the product as built. Usage and quality data will be added once VoiceSkill has been through a proper round of user testing.

05 What building it taught me

See it

Case study · VoiceSkill · Himanshu Jain← Back to all work