Dictation built for how you actually work. Talk to ChatGPT, prompt Claude, message your agents, reply to Slack and email, all by speaking. Aqua Voice turns speech into text in every app on your phone.
Powered by Avalon, our own transcription model, Aqua Voice is built for speed, accuracy, and the technical vocabulary that trips up other dictation apps.
HOW IT WORKS
Install the Aqua Voice keyboard. Open any app. Tap the mic and talk. Your words appear as text, ready to send.
POWERFUL VOICE EDITING
Edit mode lets you edit your last transcript, or your current selection, with your voice. For example:
"Remove filler words, this is a Slack message"
"Translate this to Japanese"
"Make this title case" / "make this lowercase"
"Spell Toni, T-O-N-I"
"Format the numbers like $10m"
BUILT FOR AI WORKFLOWS
The people using AI tools the most are doing it on the go: prompting ChatGPT from the back of an Uber, sending instructions to agents between meetings, running workflows that move faster than your thumbs can type.
Aqua Voice is the fastest way to get thoughts into any AI tool on your phone. Speak naturally, up to 230 WPM. We handle punctuation, formatting, and technical terms.
ACCURACY THAT MATTERS
Avalon is trained on the words you actually use: API endpoints, model names, programming terms, the jargon that makes generic dictation tools guess wrong. 97.3% accuracy on the AISpeak benchmark.
When 9to5Mac tested Aqua against Apple Dictation on the same passage, Apple made 17 errors. Aqua made 1.
WORKS EVERYWHERE
• ChatGPT, Claude, Gemini, and any AI chat
• Slack, Teams, Discord, Telegram
• iMessage, WhatsApp, Signal
• Gmail, Outlook, and every email app
• Notes, Docs, and everything else
YOUR VOICE, NOT OURS
• Personal dictionary syncs across desktop and mobile, so your names and jargon get recognized every time
• 49 languages supported
• Text starts appearing in under 50ms, final text in about 450ms
• SOC 2 Type II certified
Start free with 1,000 words. No card required.
Terms of Use: https://www.apple.com/legal/internet-services/itunes/dev/stdeula/
