Apograph

Apograph

TrustMRR

Apograph turns speech into text entirely on your iPhone. Whisper models run locally, so recordings and transcripts never leave the device: no account, no server, no analytics. Works in Airplane Mode.

Apograph turns speech into text entirely on your iPhone. Whisper models run locally, so recordings and transcripts never leave the device: no account, no server, no analytics. Works in Airplane Mode. Record or import audio and video in 99 languages, tap any sentence to replay it, edit in place, and export as text, Markdown or PDF. Every recording is a plain folder in Files. Pro is a one-time purchase that adds the Best model, speaker separation and SRT/WebVTT subtitles. No subscription.

Share card

Actual performance

Did not reach leaderboard

Launch Intel predictions

Analyze your own launch →
Product HuntOn track for Day 1 leaderboard · Strong signals: model, models, recordings · Missing: mac, agents, macos
94%94% predicted probability of success on Product Hunt, based on ML models trained on real launch data.
best fitHighest predicted score across all platforms for this description.
Indie HackersFits the IH revenue-focused audience · Strong signals: para · Missing: supports, created, podcasting
52%52% predicted probability of success on Indie Hackers, based on ML models trained on real launch data.
Hacker NewsMay not resonate with HN audience · Missing: https docs, just released, open source
40%40% predicted probability of success on Hacker News, based on ML models trained on real launch data.
AppSumoMay struggle as an AppSumo deal · Missing: reviews, intuitive, videos
33%33% predicted probability of success on AppSumo, based on ML models trained on real launch data.
BetaListMay not resonate with beta-testers · Strong signals: audio · Missing: web3, just like, small businesses
30%30% predicted probability of success on BetaList, based on ML models trained on real launch data.
Acquire.comPre-revenue stage for this audience · Strong signals: subscription · Missing: arr, mrr, revenue
17%17% predicted probability of success on Acquire.com, based on ML models trained on real launch data.
TrustMRRLess likely to generate early MRR · Strong signals: ai, best · Missing: api, 000, profitable
14%14% predicted probability of success on TrustMRR, based on ML models trained on real launch data.
nativeThis product was originally launched on this platform.

Correct prediction on native model

Similar products

Al
Aligning Whisper Transcripts with Descript38%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Aligning Whisper Transcripts with Descript

Hacker News1
PowerSearch
PowerSearch33%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Search every email account at once, entirely on-device

Indie Hackerscommitment-side-project
Wavify
Wavify85%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

On-device speech AI models that run anywhere

Product Hunt+54
Whisper AI Transcribe
Whisper AI Transcribe15%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

AI transcripts that turn recordings into reusable knowledge

Indie Hackers
An
Andrew Huberman transcripts app (OpenAI Whisper)39%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Andrew Huberman transcripts app (OpenAI Whisper)

Hacker News1
Ru
Run meteor.js locally without server71%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Run meteor.js locally without server

Hacker News4
Mi
Misheard turns "recognize speech" into "wreck a nice beach"54%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Misheard turns "recognize speech" into "wreck a nice beach"

Hacker News3
Wh
Whisper.nvim – local speech to text in Neovim33%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Whisper.nvim – local speech to text in Neovim

Hacker News1
Io
IoT and Device Analytics46%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

IoT and Device Analytics

Hacker News2
Locally AI + Qwen
Locally AI + Qwen79%Launch Intel prediction score: how likely this product is to succeed on its source platform, based on its name, tagline, and description.

Run Qwen's latest models locally on your iPhone

Product Hunt+113iOS