Wenjin Feng

Building AI App

About

Indie developer. I build tools that keep your data on your own device. SpeakText is my current project: it turns audio and video files into text and word-timed SRT subtitles entirely on the phone — 35 languages, on-device inference, nothing uploaded. I built it because every transcription tool I tried wanted me to upload the recording to someone else's server first.

Links

IOS

Android

Badges

Tastemaker

Gone streaking

Maker History

SpeakText: Voice TranscriberOffline speech-to-text. Your audio never leaves your phone.
Oct 2026

🎉

Joined Product HuntApril 25th, 2025

Forums

•

3d ago

SpeakText: Voice Transcriber - Offline speech-to-text. Your audio never leaves your phone.

Every tool I tried wanted the upload first. SpeakText does the whole job on the phone: MP4, M4A, MP3 or WAV in, word-level-timed SRT subtitles or plain TXT out. Voice activity detection, punctuation restoration and inference all run locally on sherpa-onnx. 35 languages, no cloud API, works in airplane mode. It keeps running with the screen locked and resumes if Android kills it. Editing a subtitle line seeks the player to that moment. 3-day free trial.