Whisper Direct

WhisperDirect: High-Accuracy Speech-to-Text and Summarization App

WhisperDirect is a high-accuracy speech-to-text and summarization app that allows users to transcribe and summarize audio and video content using their own OpenAI API key. The app offers a cost-effective, pay-as-you-go model with no subscription required, making it an affordable alternative to traditional subscription-based services.

Key Features

• Record and Transcribe: Record audio directly within the app or import audio and video files from various formats.
• Playback-Synced Highlighting: Playback-synced highlighting of transcript segments for easy navigation.
• Timeline Markers: Insert configurable timeline markers in 5-second steps.
• Summarization and Meeting Minutes: Generate summaries and meeting minutes using customizable prompts.
• Export Options: Export audio, text, summaries, minutes, or subtitles in various formats (VTT / SRT).
• Slack Integration: Automatically post transcripts, summaries, and minutes to Slack.
• Cost Estimation: Estimate costs based on audio length and character count.
• Customization: Customize LLM models, timeline intervals, prompts, and other settings.

Supported Formats

• Audio: mp3, m4a, aac, wav, flac, ogg, opus, wma, amr, mpga, webm, aiff, caf
• Video: mp4, mov, m4v, webm, mkv, avi, mpeg, mpg

Pricing and Trial

• Free Trial: 5 sessions included.
• One-Time Purchase: Unlock unlimited use of current features with a one-time in-app purchase.
• API Usage: Billed directly by OpenAI; the app does not charge for API usage.

Cost Guide

• Transcription: With $5, you can transcribe about 14 hours of audio.
• Whisper API: Approximately $0.006 per minute (approximately $0.36 per hour).
• OpenAI API Pricing: For detailed pricing, visitOpenAI API Pricing.

Models for Summaries and Meeting Minutes

Choose from compact, low-cost models:- GPT-4.1-nano- GPT-4.1-mini- GPT-5-nano- GPT-5-mini

Even long texts (1,0002,000 words) can usually be processed for just a few cents per run.

Compatibility

• iPhone: Requires iOS 17.0 or later.
• Mac: Requires macOS 14.0 or later and a Mac with Apple M1 chip or later.
• Apple Vision: Requires visionOS 1.0 or later.

Privacy

The developer, koji ozono, indicated that the apps privacy practices may include handling of data as described below. For more information, see the privacy policy. The developer does not collect any data from this app.

Whats New

Version 1.1.17 (Oct 1, 2025)- Fixed crashes when running on macOS.

Developer Information

• Developer: koji ozono
• Size: 31.6 MB
• Category: Productivity
• Languages: English, Japanese
• Age Rating: 4+
• Price: Free with in-app purchases (Unlock Full Version $3.99)

Notes

• An API key (such as OpenAI) is required.
• Pricing and available models may change according to OpenAIs offerings.

For more information, visit theWhisperDirect Product Hunt page.