# How to Use Claude's Voice Mode

A guide to interacting with Anthropic's AI assistant through voice commands.

- **Source:** [Engadget](https://www.engadget.com)
- **Published:** 2026-08-09
- **Topic:** [Data & AI](https://brifing.si/c/data-ai)
- **Original article:** <https://www.engadget.com/2231293/how-to-use-claude-voice-mode/>
- **On Brifing:** https://brifing.si/s/c4636285-e4a3-461e-abc3-7b40186f4da4

## Introduction to Voice Mode

Anthropic has offered voice mode for its Claude AI assistant since 2025. The July 2026 update made the feature more useful. Initially only working with the low-latency Haiku model, voice mode now supports more powerful models like Sonnet and Opus. Users can get smarter responses by pulling context from connected apps. This evolution marks significant progress in voice-enabled AI interactions.

## How to Activate

Voice mode is available on Claude's mobile (Android/iOS) and desktop apps, as well as the web interface. The feature performs best on phones. To activate, simply tap the black waveform icon in the lower right corner (not the adjacent microphone icon). The mode stays active until you press 'Stop'. This intuitive activation makes voice interaction accessible even for less tech-savvy users.

## Key Difference from ChatGPT

Claude's voice mode uses a 'turn-based' architecture where the AI listens first then responds, unlike ChatGPT's 'duplex' system that processes speech and generates outputs simultaneously. Brief pauses might be mistaken for the end of questions in Claude. Anthropic recommends asking multi-part questions separately. This architectural choice reflects different approaches to conversational AI design.

## Model Options

Users can switch between Claude models using the selector at the bottom. Opus model handles complex tasks but requires paid subscription. Free accounts can use Haiku and Sonnet models, with Sonnet being sufficient for most prompts. Voice conversations count against usage limits. This tiered access allows users to choose appropriate computational power for their needs while managing costs.

## Connected App Integration

Voice mode works with connected apps like Gmail, Google Calendar and Slack. You can request summaries of recent emails, for example. First-time access requires granting permissions. Simply specify which app to use in your prompt. This integration significantly boosts productivity by enabling voice-controlled access to frequently used services, creating seamless workflows.

## Language and Voice Options

As of July 2026, voice mode supports 14 languages with some offering additional dialects. Selected language affects Claude's voice options (e.g., 5 English voices vs 2 Japanese). Users can change preferences in Settings. Mid-sentence language switching isn't automatically detected. This multilingual support makes Claude accessible to global users while highlighting current technical limitations.

## Voice Settings and Recording Modes

Users can adjust Claude's speech speed (Slow/Normal/Fast) and choose between 'Hands free' and 'Push to talk' recording modes. Anthropic recommends 'Hands free' in quiet environments. Each voice option can be previewed. These customization features allow personalization of the interaction experience, making the AI assistant feel more natural and responsive to individual preferences.

## Free vs Paid Usage

Voice mode doesn't require Pro/Max subscription but free accounts are limited to Haiku and Sonnet models. Free users can access all supported languages but only connect one app. Opus model requires paid subscription. This tiered model provides flexibility while encouraging upgrades for power users needing advanced capabilities, balancing accessibility with monetization.

## Sources covering this story

- https://www.engadget.com/2231293/how-to-use-claude-voice-mode/ — 

---

_Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._