CodexUse logo CodexUse Download

Voice dictation: speak prompts with local Whisper

CodexUse 2.5 adds voice-to-text dictation powered by Faster Whisper running entirely on your machine. Download a model, click the mic, and speak your prompt. The transcription flows into the composer and nothing leaves your device.

Key takeaway: All speech processing is local. No audio is sent to any server. You control which model is downloaded and used.

How it works

Supported models

Model Size Speed Accuracy
tiny ~39 MB Fastest Basic
base ~74 MB Fast Good
small ~244 MB Moderate Better
medium ~769 MB Slower Strong
large-v3 ~1.5 GB Slowest Best

Managing models

  1. Go to Settings → Chat → Dictation.
  2. You will see the list of available models with download/remove buttons.
  3. Click Download to fetch a model. Progress is shown inline.
  4. Click Cancel to abort an in-progress download.
  5. Click Remove to delete a downloaded model and free disk space.

You can have multiple models downloaded and switch between them as needed.

Using dictation

  1. Make sure at least one model is downloaded.
  2. Focus the chat composer (workspace home or active chat).
  3. Click the microphone button or use the keyboard shortcut.
  4. Speak your prompt. The transcribed text appears in the composer.
  5. Edit the text if needed, then send as usual.

Smart text insertion

Dictation handles text insertion thoughtfully:

Privacy

Troubleshooting

Symptom Likely cause Action
Mic button disabled or missing No model downloaded Go to Settings → Chat → Dictation and download at least one model.
Transcription is inaccurate Using a small model or noisy environment Try a larger model (small, medium, or large-v3). Reduce background noise.
Dictation is slow Large model on limited hardware Use a smaller model. The tiny or base models are fast on most machines.
Python error on startup Missing Python or dependencies Ensure Python 3 is installed. The dictation script requires the faster-whisper package.

Related

Does dictation send audio to the cloud?

No. All speech-to-text processing happens locally on your machine using Faster Whisper. No audio data is transmitted anywhere.

Which Whisper model should I use?

For fast results with reasonable accuracy, the base or small model works well. For best accuracy on longer dictation, use medium or large-v3. The tiny model is fastest but less accurate.

Can I use dictation in the terminal?

Dictation is available in the chat composers (workspace home and active chat). It does not inject text directly into the integrated terminal.

Download CodexUse - free (2 profiles, 2 projects)