Simple extension for gemini cli to add a speech-to-text and text-to-speech loop for prompt and response.

[sandipchitale]

This extension cc-gc-stts for gemini cli implements speech-to-text and text-to-speech loop for prompt and response. See README for details.

To try it:

gemini extensions install --consent https://github.com/sandipchitale/cc-gc-stts.git

Prompt (speech-to-text)

Response (text-to-speech)

Uses a controlled chrome window to make use of the web API for speech-to-text and text-to-speech.

Feedback welcome!

[sandipchitale]

I am trying to make this work with agy but it did not work even though it seems to import it but it does not actually work:

agy plugin import gemini --force

[sandipchitale]

The import did not work. I had to implement plugin.json as described here and convert command (.toml) to SKILL.md manually.

[aniruddhaadak80]

Hey there. Thanks for sharing this.

Building integrations on top of the CLI is exactly what we love to see. This looks like a really solid approach.

If you have a GitHub repository for this project, definitely drop the link here.