Claude Code adds voice mode for hands-free coding commands

Anthropic has launched voice mode for Claude Code, its AI coding assistant for developers. The feature enables hands-free, conversational coding workflows through spoken commands.
Key details from the source
According to engineer Thariq Shihipar's announcement on X:
- Voice mode is currently live for approximately 5% of users
- Broader rollout is planned for the coming weeks
- To enable: type
/voiceto toggle it on, then speak your command - Example command: "refactor the authentication middleware"
- Users will see a note on the welcome screen once they have access
The source notes several unknowns about the implementation:
- Limitations of the capability are unclear
- It's unknown if there are caps on voice interactions or specific technical constraints
- It's unclear if the feature was built with a third-party AI voice provider like ElevenLabs
Anthropic previously launched voice mode for its standard Claude chatbot in May, allowing voice interaction for general-purpose tasks. The company reported in February that Claude Code's run-rate revenue surpassed $2.5 billion, more than doubling since the beginning of 2026, with weekly active users doubling since January.
📖 Read the full source: HN AI Agents
👀 See Also

US Job Losses Tied to AI Exposure Begin Mounting, Bloomberg Reports
Bloomberg reports that the US is seeing significant job losses in roles exposed to AI, with a Hacker News discussion pointing to real-world impact on developers and other knowledge workers.

Anthropic Allows Subscription Usage for Claude via OpenClaw Starting June
Anthropic will allow subscription-based usage of Claude through OpenClaw starting in June, as announced by the OpenClaw Dev Twitter account.

CEOs Who Think AI Replaces Their Employees Are Just Bad CEOs
CEO Aaron Levie explains 'AI psychosis' — when leaders, detached from real work, see happy-path demos and overestimate agentic tools like Claude Code, ignoring the last mile of production.

Fable 5 Wins on Real-World Fraud Detection: Claude 4.x Family vs GPT-5.5 Benchmarked
Five frontier models (Fable 5, Opus 4.8, Sonnet 4.6, Haiku 4.5, GPT-5.5-high) were given the same cold prompt to audit live crowdfunding campaigns on zooid.fund. Only Fable 5 verified claims against the open web, catching duplicate creators and real-world events.