WhisperDirect is a high-accuracy speech-to-text app that works with your own API key, so you pay only for what you use with low, flexible, usage-based pricing.
Now with Slack integration: automatically post transcripts, summaries, and meeting minutes to your selected channel.
🚀 Get it on the App StoreNo subscriptions — low-cost pay-as-you-go with your OpenAI key. Fast, accurate transcription. Summaries, minutes, Slack posting & subtitle export.
About $0.006 per minute (≈ $0.36 per hour), based on OpenAI’s official rates as of July 2025.
Uses GPT-4.1 GPT-5 (nano, mini) models. Summarizing even several thousand words of English text typically costs only a few cents (varies by input length).
Pricing follows OpenAI’s pricing and may change. See details.
Record with the mic button and transcribe instantly.
Import audio files and convert them to text.
Import directly from the iOS share sheet.
Bring in video files — audio is extracted and compressed automatically.
Automatically record each file’s duration and size after import/convert.
Playback-synced auto-highlight of the current transcript segment.
Insert markers at a custom interval (configurable in 5-second steps in Settings).
Generate summaries and meeting minutes (prompts are editable in Settings).
Export audio / text / summaries / minutes.
Automatically post transcripts, summaries, and minutes to Slack.
Export subtitles (VTT / SRT).
Check an estimated cost in Settings (based on audio length and character count).
Automatically back up audio and transcripts to Google Drive. Sync seamlessly with your PC or other devices.
Audio: mp3, m4a, aac, wav, flac, ogg, opus, wma, amr, mpga, webm, aiff, caf
Video: mp4, mov, m4v, webm, mkv, avi, mpeg, mpg
This app requires an API key (e.g., OpenAI). Charges are billed according to each service’s pricing policy.