Speech FAQs

Question 1

What are the key features of Speech?

Accepted Answer

Key features include a modern PyQt-based UI, voice input using faster-whisper, voice output with 54+ voices via Kokoro TTS, multi-speaker narration, and audio/video transcription.

Question 2

Can Speech transcribe audio and video files?

Accepted Answer

Yes, Speech can transcribe audio and video files using faster-whisper. It supports various formats and offers features like timestamps and speaker detection.

Question 3

What is Speech MCP?

Accepted Answer

Speech MCP is a Goose extension that allows users to interact with the Goose platform using their voice. It features real-time audio processing, speech-to-text, and text-to-speech capabilities.

Question 4

What is Kokoro TTS and why is it used?

Accepted Answer

Kokoro TTS is a high-quality text-to-speech engine used by Speech to provide a wide range of natural-sounding voices for converting text into speech.  It supports over 54 voice options.

Question 5

How do I install Speech MCP?

Accepted Answer

You can install Speech using the Goose CLI, a one-click install link, or manual installation. Ensure you install PortAudio as a prerequisite before installing Speech.

Speech

主な機能

ユースケース

Speech

主な機能

ユースケース