Speech (STT & TTS)

Pia includes local speech processing — no cloud APIs required.

Speech-to-Text (STT)

Powered by Whisper running locally on your machine.

Setup

1. Open Settings → General
2. Choose a Whisper model size from the Whisper Model dropdown (Tiny, Base, Small, Medium)
3. Click Download to download the model
4. Select your language from the Speech-to-Text Language dropdown
5. Click the microphone icon in the chat to start recording

Tip

Start with the Base model for a good balance of speed and accuracy. Larger models are more accurate but slower.

Text-to-Speech (TTS)

Powered by Piper for local, offline voice synthesis.

Downloading a Voice

1. Open Settings → Text-to-Speech
2. Scroll through the voice list — each card shows the voice name, language, gender, and quality
3. Find a voice you like and click Download
4. Wait for the progress bar to finish

You can download as many voices as you want.

Selecting a Voice

1. Once a voice is downloaded, click Select to make it your active voice
2. The card will show an Active badge to confirm it’s in use

Only one voice can be active at a time. To switch, just select a different downloaded voice.

Using TTS

Once a voice is active, AI responses will be read aloud automatically.

Privacy

All speech processing happens locally on your device. Audio is never sent to external servers.