WhisperStream is your complete audio solution, featuring both speech-to-text transcription and text-to-speech synthesis using Chatterbox voice mimic technology.
WhisperStream is a download available to all Story Runner members.
Join today!
Convert spoken audio into accurate text transcriptions using advanced Whisper AI models. Support for single files and batch processing.
Transform text into natural-sounding speech using Chatterbox voice mimic technology. Create custom voices and process text in batches.
Process dozens of audio files for transcription or text files for speech synthesis at once. Monitor progress and export all results efficiently.
Choose the right Whisper models for transcription and Chatterbox voices for synthesis. Download, update, or remove models with a single click.
Trouble installing? Run diagnostics to check Python, Whisper, Chatterbox, FFmpeg, and network status. One-click fixes for common issues.
All processing happens locally on your PC. No cloud processing, no additional AI charges, complete privacy for your audio and text.
Select from multiple Whisper AI models for transcription or Chatterbox voices for speech synthesis. Download new models and voices as needed.
For transcription: Add audio files. For synthesis: Add text files. Process single files or add a whole batch. Preview audio with the built-in media player.
Start transcription or synthesis. Watch progress in real time and review results as they complete.
Save transcriptions as text or export synthesized speech as audio files. Batch export supported for both workflows.
No. All speech recognition and synthesis runs locally on your PC. Internet is only required for downloading models, voices, or updates, and is never used for processing your audio or text.
Yes! WhisperStream's batch mode lets you add and process dozens of audio files for transcription or text files for speech synthesis in one go, with progress tracking and easy export of all results.
Chatterbox is advanced voice mimic technology that can create natural-sounding speech from text. It can clone voices and generate speech that sounds remarkably human-like.
Absolutely. All transcription and synthesis is done locally on your PC. No audio or text data is ever sent to external servers.
Use the built-in diagnostics to check your setup and fix common issues with Python, Whisper, Chatterbox, or FFmpeg. StreamTeem Discord community is also here to help.
Yes! With Chatterbox TTS, you can train custom voice models or use pre-trained voices to generate speech in different styles and accents.