Proso per Pedro Balbino

Proso is a Firefox-first reader that turns web pages and selected text into speech while keeping playback controls on the page.

What it does

• Extracts article text or reads a selection.
• Starts from the popup, a selected paragraph, a keyboard shortcut, or the context menu.
• Highlights the current paragraph and word while audio plays.
• Supports pause, resume, stop, speed, seek, previous/next paragraph, and a reading queue.
• Caches generated audio locally and can export audio/highlights.
• Works without a Proso account through BYOK or a synthesis host you operate.

Choose your audio route

• Bring an OpenAI, ElevenLabs, Groq, or Cartesia API key.
• Enter the address of a synthesis host you operate; Proso requests the narrowest Firefox host permission and sends text only to that exact configured destination.
• Eligible plans may use Proso-managed synthesis.

Reading necessarily sends the text you ask to hear to the selected synthesis destination. Nothing is sent until you start reading. The public AMO build sends no usage telemetry, interaction analytics, browsing history, or page URLs to Proso.

Firefox 109 or later is required. An API key, configured synthesis host, or eligible managed plan is required to generate audio.