Microphone recording

Turn Your Voice Into Text — Effortlessly

WhisperStream is an easy and fast to use tool when your creativity leads you to translate spoken word to text.

WhisperStream is a download availble to all Story Runner members. Join today!


Become a Story Runner
screenshot
screenshot

Why WhisperStream?

Batch

Batch Transcription

Transcribe dozens of audio files at once. Monitor progress, retry failed jobs, and export all results in your preferred format.

Model

Model Manager

Choose the right Whisper model for your needs. Download, update, or remove models with a single click.

Diagnostics

Built-in Diagnostics

Trouble installing? Run diagnostics to check Python, Whisper, FFmpeg, and network status. One-click fixes for common issues.

Privacy

Private & Local

All processing happens locally on your PC. Without additional AI charges.

How It Works

1. Choose Your Model

Select from multiple Whisper AI models for the right balance of speed and accuracy. Download new models as needed.

2. Add Audio Files

Transcribe a single file or add a whole batch. Preview audio with the built-in media player.

3. Transcribe & Review

Start transcription.
Watch progress in real time.

4. Export & Use

Save or copy paste your transcript text. Batch export supported.

Ready to rip text right from your voices?

Frequently Asked Questions

Does WhisperStream need the internet?

No. All speech recognition runs locally on your PC. Internet is only required for downloading models or updates, and is never used for processing your audio.

Can I transcribe multiple files at once?

Yes! WhisperStream’s batch mode lets you add and process dozens of files in one go, with progress tracking and easy export of all results.

Is my data private?

Absolutely. All transcription is done locally.

What if something doesn’t work?

Use the built-in diagnostics to check your setup and fix common issues with Python, Whisper, or FFmpeg. StreamTeem Discord community is also here to help.