#Voice — Speaking & Listening

Why type when you can talk? And why read when the AI can read to you? Your hands are busy holding groceries, stirring risotto, or just being lazy. We don't judge.

#What It Does

Voice in ambientChat works in both directions. You can speak your questions instead of typing them, and the AI can read its answers aloud instead of making you squint at text. It turns your AI assistant into something closer to an actual conversation — one where the other party happens to know the entire contents of your pantry.

Voice Input uses speech recognition to transcribe what you say into a text message, which then gets sent to the AI just like a typed message. You speak, it types, the AI answers.

Voice Output uses text-to-speech (TTS) to read the AI's responses aloud. The same voice — and the same style instructions — is used everywhere the app speaks: chat auto-play, the speaker icon on older chat messages, beacon-triggered room narrations, and the preview button in Voice Settings. Change your voice or style once and it applies everywhere, immediately.

#How to Use It

#iOS App

#Speaking to the AI (Voice Input)

1. Open the Chat tab
2. Tap the microphone button next to the text input field
3. Speak your question clearly — a recording indicator shows the app is listening
4. When you finish speaking, the app transcribes your words into text
5. The transcribed message appears in the text field, and is sent automatically
6. The AI responds as usual, with full access to your inventory, documents, and context

You can speak naturally. "What's expiring this week?" works just as well spoken as typed. The AI doesn't care about your accent — it's heard worse.

#Listening to the AI (Voice Output)

1. When the AI sends a response, a speaker icon appears on the message bubble
2. Tap the speaker to have the response read aloud
3. Tap the speaker a second time (on any message) to stop playback
4. With Auto-speak enabled, responses play automatically as they arrive
5. Tapping the speaker on an older message generates fresh audio on demand if your voice or style has changed since the message was first spoken

Audio routes to your main speaker (or Bluetooth / wired headphones when connected). If you were just using voice input, the session switches back to speaker playback automatically — you shouldn't have to hold the phone to your ear.

#Voice Settings

1. Go to Account → Voice Settings
2. Here you can:
   • Choose a voice — pick from Ash, Fable, Marin, Onyx, Sage, or Verse. Tap a voice to preview it.
   • Set a voice style — optional free-text instructions the AI applies to how the voice speaks (for example, "speak warmly" or "sound excited about recipes")
   • Enable Auto-speak — when on, AI responses play automatically. When off, tap the speaker icon on any message to listen.

Settings apply across every place the app speaks. You do not need to change the voice in more than one place.

#Via Chat

Voice input and text input produce identical results. The AI doesn't know or care whether you typed or spoke — it receives the same text either way. So every example prompt in every other guide in this knowledge base works with voice too. Just say it instead of typing it.

Some particularly useful voice scenarios:

• "What's expiring this week?" (while unpacking groceries)
• "What spices do I have that go with salmon?" (while staring at salmon)
• "Read me the warranty details for my laptop." (while on hold with tech support)
• "Add a note: I put the Christmas decorations in the garage attic." (while climbing down a ladder)

#Tips & Tricks

• Speak clearly and in a reasonably quiet environment. Speech recognition is impressive but not magical. Background noise, heavy accents, and mumbling all reduce accuracy. If the transcription comes out garbled, you can always edit it before sending.
• Voice output is great for hands-free workflows. Cooking, organizing the garage, or sorting through boxes — any time your hands are occupied but your ears are free, voice output turns the AI into a helpful narrator for your life.
• You can interrupt playback anytime. Tap the speaker icon to stop. No need to sit through the whole thing politely — the AI won't be offended.
• Changed your mind about a voice? Tap the speaker icon on an older message and the app regenerates the audio in your new voice and style. Messages spoken with a previous voice keep their old audio until you ask for it fresh.

#Options

#Known Limitations

• Voice input requires an internet connection. Speech recognition happens on Apple's servers, so it won't work in airplane mode or without network access. If you're offline, you'll need to type.
• No wake word. You can't say "Hey ambientChat" to activate voice input. You need to tap the microphone button first. This is an intentional design choice — the app doesn't listen until you tell it to.
• Long responses may take a moment before audio starts. The TTS engine needs to process the response before playback begins. For particularly lengthy AI answers, there may be a brief pause before you hear anything.
• Voice input transcription accuracy varies. Product names, brand names, and technical terms may not transcribe perfectly. Review the transcribed text before it sends if accuracy matters for your query.
• Tapping the speaker on an older message may regenerate audio. If you changed your voice or style after that message was first spoken, the app needs to fetch a fresh recording — expect a brief delay on first tap. Subsequent taps of the same message use the cached audio.

#Version History