🎙️ Speak and Listen: Voice and Audio Interaction

Forget the keyboard. With YuIA's voice and audio features, you can interact in the most natural and fluid way there is: by speaking. Dictate your ideas, listen to responses with realistic voices, and even have a continuous dialogue, as if you were on a call.

Discover the different interaction modes and turn YuIA into your conversation partner.

🚀 Want to test it now? Start a voice call right in your browser and talk to the AI without typing anything.

🎙️ Speech Transcription: Send Messages with Your Voice

Ideal for: Dictating long messages, taking quick notes, or simply when you don't feel like typing.

Convert your speech to text with precision.

1. In the text box, click the Microphone icon (🎙️).
2. Speak your message clearly.
3. Your speech will be converted to text and appear in the message box for you to review, edit, and send.

tip

⚡ Speed up your sends! Don't want to review each message? Go to Settings > Audio and enable Instant Auto-Send After Voice Transcription. This way, after a brief silence, your message will be sent automatically.

🔊 Read Aloud: Listen to AI Responses

Ideal for: Multitasking. Listen to responses while doing other things, or simply to give your eyes a rest.

Turn any text into audio with a click.

1. At the end of any AI response, click the speaker icon (🔊).
2. The response will begin to be read aloud with a natural voice.

tip

⚙️ Choose your preferred voice! You can customize the assistant's voice. Go to Settings > Audio > Set Voice to select the one you like best.

Available voices include: alloy, echo, shimmer, ash, ballad, coral, sage, and verse, each with a different tone and personality. Experiment until you find the one that matches you best!

You can also adjust the playback speed in Settings > Audio to listen faster or slower, according to your preference.

🎧 Voice Mode: Converse in Real Time

Ideal for: A fully immersive, hands-free experience, like a phone call with your AI.

This mode combines transcription and audio to create a continuous and fluid dialogue.

1. To start, click the headphone icon (🎧).
2. Start speaking. The AI will listen, think, and respond by voice, without you needing to click anything else.

tip

😊 Expressiveness and Quick Access

• Emoji on Call: Want the AI to be more expressive? Enable Show Emoji on Call in Settings > Interface so it uses emojis during voice calls.
• Direct link access: Save this link as a shortcut on your phone to start a voice call directly, without navigating through the interface.
• Voice/Touch Interruption: The AI is speaking, but you want to say something else? Simply start talking over it or tap the phone screen to interrupt it instantly.

🎥 Video Calls: Converse with Vision

Ideal for: Getting help with the real world, showing objects, or analyzing what's around you.

Take the interaction to another level by conversing with models that have vision.

1. Select a vision-compatible model.
2. Start a voice or video call.
3. Turn on your camera and show the AI what you're seeing. Ask it to describe an object, translate a menu, or help you fix something.

🎵 Transcribe Audio Files

Ideal for: Turning recordings of classes, meetings, interviews, or voice memos into text.

Don't limit yourself to speaking in real time. Upload existing audio files for analysis.

1. Drag and drop an audio file (.mp3, .m4a, .wav, etc.) directly into the chat.
2. YuIA will transcribe all the content to text.
3. Then, you can ask the AI to summarize, extract key points, or answer questions about the recording's content.
4. From there, you can ask the AI to summarize the key points, identify who spoke, or extract key information from the transcription.