Voice mode - CLI - Docs - Kiro Loading image... Product * About Kiro * IDE * CLI * Web * Mobile * Crew * Pricing * Downloads For * Enterprise * Startups * Students Community * Overview * Ambassadors * Discord * Events * Powers * Shop * Showcase Resources * Docs * Blog * Changelog * FAQs * Report a bug * Suggest an idea * Billing support Social * * * * * * * English Site Terms License Responsible AI Policy Legal Privacy Policy Cookie Preferences English Loading image... * Apps * CLI * Web * Enterprise * Pricing * Docs * Community * Resources SIGN IN DOWNLOADS Loading image... Get Started Installation Authentication Your first project Models Overview Available models Reasoning effort Features How Kiro works Specs Steering Hooks MCP Permissions Custom agents Agent Skills Powers Cloud sessions Compaction Kiroignore Checkpoints and rewind Built-in tools Configuration scopes IDE 1.x What's new in 1.0 Setup & First Run Editor Chat Experimental Troubleshooting 0.x reference CLI What's new in 3.0 Setup & First Run Terminal UI Chat Voice mode Headless mode ACP Auto complete Experimental 2.x reference Crew Quick start Installation Running 24/7 Chat Agent Capabilities Features Interfaces Apps System & storage Configuration Security Troubleshooting Web Setup & First Run Identity Center Connect your repositories Working with the agent Autonomous mode Automations Memory Configuration Sync Sandbox Mobile - Preview Overview Commands and Reference CLI commands Slash commands Built-in tools Exit codes Settings Billing Overview Managing your subscription Upgrading your plan Downgrading your plan Cancelling your plan Purchasing add-on credits Managing your payments Managing usage notifications Managing your taxes Contacting billing support Deleting your account Related questions Enterprise Concepts Onboarding quickstart Connecting your identity provider Deployment options Subscribe your team Manage subscriptions Governance Monitor and track Settings Managed updates Billing IAM Supported regions Privacy and Security Overview Data protection Code references Compliance validation Infrastructure security IAM permissions Firewalls, proxies, and data perimeters VPC endpoints (AWS PrivateLink) Guides Overview Language support Learn by playing Migration Migrating from Q Developer Migrating from VSCode Upgrading from Q CLI * Docs * * CLI * * Voice mode Copy page View as Markdown Voice mode Copy page View as Markdown Voice mode lets you speak your prompts instead of typing them. Your speech is transcribed locally with OpenAI Whisper (via whisper.cpp ) and, by default, submitted to the assistant automatically. You can switch to review-before-send if you prefer. It runs entirely on your machine by default, so no audio leaves your computer and no cloud API key is required. The speech model downloads once, on first use. Info Voice mode is a speech-to-text input feature for the Kiro CLI. It requires a microphone (or a remote voice server for cloud desktops) and a build of kiro-cli with the voice feature compiled in. This is separate from voice in KiroCrew, which offers both speech-to-text and text-to-speech in the dashboard. How it works * Start a recording with /voice or by holding Space . * Speak your prompt while the recording indicator shows your audio level in real time. * Stop by pressing Enter , or let it auto-stop after a period of silence. * The transcription is submitted to the assistant automatically by default, or placed in the prompt for review when you set voice.autoSubmit false . Recording, press ENTER when done... 3.5sec ░░░█████████ Partial text streams into the input as you speak, so you can watch the transcription form before you stop. Starting voice input Slash command /voice Starts a single recording session in the current chat. Push-to-talk with Space Hold the Space key at the prompt for 1.5 seconds to start recording. Release Space to stop and transcribe. Useful for a quick voice input without pressing Enter . First run: downloading the speech model The Whisper model is downloaded on first use, and the download is never silent. 1 Run /voice The command detects that no model is present. 2 Confirm the download A panel shows the model name, its size (about 148 MB for the default base model), and its license (MIT). Press y to download or n to cancel. 3 Voice is ready The model is cached under ~/.cache/kiro/models/ . Subsequent recordings start instantly. If you trigger voice with Space (push-to-talk) before the model is downloaded, Kiro prompts you to run /voice for the interactive setup. Info In headless or piped invocations there is no interactive panel. Pass --confirm-download on the CLI command directly to approve the one-time download. Transcription backends Local Whisper (default) Local transcription uses whisper-rs (Rust bindings for whisper.cpp) and needs no internet after the initial model download. Two model sizes are available: Model Download size Speed Accuracy base (default) ~148 MB Faster Good small ~466 MB Slower Better Set the model size: bash kiro-cli settings set voice.modelSize small Remote voice server (for cloud desktops) When you work on a cloud desktop with no microphone, voice mode can stream audio to a small server running on your local machine. Voice mode falls back to the remote server automatically when no local microphone is detected. Manual setup: bash # On your local machine (the one with a microphone): kiro-cli voice-serve # Open a reverse tunnel when you SSH to the cloud desktop: ssh -R 19876 :localhost:19876 cloud-desktop # On the cloud desktop, point voice mode at the tunnel before starting Kiro: export KIRO_VOICE_SERVER_URL = http://127.0.0.1:19876 kiro-cli You can also force the remote backend for a single session with /voice --model remote (the default is --model local-whisper ). Cloud setup helper From your local machine, voice-cloud-setup starts the local voice server and opens the reverse tunnel: bash kiro-cli voice-cloud-setup < cloud-hostname > Then, on the cloud desktop, set the server URL in the same shell before starting Kiro and activating voice mode: bash export KIRO_VOICE_SERVER_URL = http://127.0.0.1:19876 kiro-cli The helper verifies SSH connectivity, starts voice-serve locally, and opens the reverse tunnel. It does not currently configure voice.serverUrl on the cloud desktop. Option Description --port <port> Port for the voice server (default: 19876 ) --remote-bin <path> Path to kiro-cli on the cloud desktop -i <identity> SSH identity file Info Set KIRO_VOICE_SERVER_URL on the cloud desktop before starting Kiro. When it is set, the local voice binary is skipped and audio streams to the server. Add the export to your shell profile if you want it to persist across sessions. Accuracy: VAD and context Voice mode uses Silero Voice Activity Detection to tell speech from background noise. It detects when you start and stop talking, filters out keyboard clicks and fan noise, and drives the silence auto-stop, which prevents false transcriptions from ambient sound. Recent conversation context is also passed to Whisper's initial prompt, which improves accuracy for code identifiers, function names, and project-specific vocabulary discussed earlier in the session. Configuration Voice behavior is controlled through kiro-cli settings . All settings are optional. Setting Type Default Description voice.modelSize string base Whisper model size: base or small voice.language string en Transcription language ( auto to detect) voice.silenceTimeout integer 5 Seconds of silence before recording auto-stops voice.maxSessionTime integer 300 Maximum recording length in seconds voice.autoSubmit boolean true Submit the transcription automatically instead of placing it in the input for review voice.serverUrl string none Remote voice server URL for cloud desktops Examples: bash # Favor speed kiro-cli settings set voice.modelSize base kiro-cli settings set voice.silenceTimeout 3 # Favor accuracy kiro-cli settings set voice.modelSize small kiro-cli settings set voice.silenceTimeout 8 # Review each transcription before it is sent kiro-cli settings set voice.autoSubmit false # Transcribe Spanish kiro-cli settings set voice.language es # View your voice settings kiro-cli settings list | grep voice Privacy and security * With local Whisper, audio is captured, transcribed, and discarded on your machine. Nothing is sent to any server. * The remote voice server option streams audio only to the server URL you configure (typically your own laptop over an SSH tunnel). * Kiro verifies the Whisper model file against a pinned SHA-256 digest after download and before every use. A corrupt, tampered, or attacker-planted model is rejected. If a cached model fails the check, Kiro deletes it and re-downloads from the official CDN automatically. No action is needed. * On Unix systems, the model directory is restricted to owner-only access (mode 0700 ) as defense in depth. Examples Basic voice input > /voice Recording, press ENTER when done... 2.1sec ░░░████████ "Fix the bug in the authentication module" > Analyzing the authentication module... Push-to-talk continuing a typed prompt * Type the start of your prompt: How do I * Hold Space and speak: "implement pagination in the users API" * Release Space to stop and transcribe * The submitted prompt reads: "How do I implement pagination in the users API" Limitations * Requires a physical microphone, or a remote voice server for cloud desktops. * Local transcription is CPU-bound. The small model is more accurate but slower, and there is no GPU acceleration yet. * Optimized for English by default; multilingual support is limited. * No wake word activation. Troubleshooting Problem Fix "No microphone detected" Grant microphone permission, or set up a remote voice server on a cloud desktop Recording stops too early Increase voice.silenceTimeout (for example, to 10 ) Poor transcription accuracy Switch to the small model, speak clearly, and reduce background noise First use is slow The model downloads once on first use, then recordings start instantly "Model integrity check failed" Kiro deletes the invalid file and re-downloads automatically. If it persists, check your network or proxy "Voice binary not found" Reinstall kiro-cli , or confirm KIRO_CHAT_CLI_BIN points to a build with the voice feature compiled in High CPU during transcription Use the base model and let a transcription finish before starting new work Related * Chat : the interactive session that voice input feeds into * Terminal UI : the interface that renders the live recording indicator * In-session settings : adjusting settings during a session Custom diff tools Headless mode