Answer: Voice input (STT) is enabled through Settings → Voice, where you can choose the model (base by default) and configure options like the microphone and dictation key. The local provider works in-process with no external binary required, and dictation works on macOS desktop installs. Status: Confirmed Entry: tool/kiro/settings/enable-voice-input-stt Revision: 2 Digest: sha256:e21ac9fbf63bd6bb (changes whenever the content changes) Timeline: Created: 2026-11-13T03:38:27Z Last changed: 2026-11-20T13:22:57Z (key start default: — → on by default) Last verified: 2026-11-20T13:22:57Z Next check: 2026-11-21T13:22:57Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of settings location | Settings → Voice | [1] | 2026-11-20 default model | base | [1] | 2026-11-20 base model download size | ~148 MB | [1] | 2026-11-20 turbo model download size | ~1.6 GB | [1] | 2026-11-20 platform support | macOS desktop installs | [1] | 2026-11-20 silence finalization time | approximately 1.5 seconds | [1] | 2026-11-20 live text default | on by default for new installs | [1] | 2026-11-20 key start default | on by default | [1] | 2026-11-20 Sources: [1] Amazon Web Services. "Voice - Chat - Crew - Docs - Kiro". https://kiro.dev/docs/crew/chat/voice/ Role: primary. Accessed: 2026-11-20T13:22:57Z Quote: "open Settings → Voice and choose Download decoder" (Supports: settings location) Quote: "The default for new installs is base ." (Supports: default model) Quote: "base (default) ~148 MB Fast, works well for most dictation" (Supports: base model download size) Quote: "turbo ~1.6 GB Higher accuracy" (Supports: turbo model download size) Quote: "Dictation works on macOS desktop installs." (Supports: platform support) Quote: "Silence for approximately 1.5 seconds finalizes the utterance." (Supports: silence finalization time) Quote: "Live text is on by default for new installs." (Supports: live text default) Quote: "Use a key to start dictation is on by default." (Supports: key start default) Published: 2026-11-20T07:39:25Z Snapshot SHA-256: edc9054e719c6f02fc6e9fb7eb2835446aafe1701bb86a6ee6be055261f7655d (captured 2026-11-20T13:22:57Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. Cross-check: not-available at 2026-11-20T13:22:57Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:22:57Z Last attempt: 2026-11-20T13:22:57Z Notes and limitations: Extracted automatically from a single official source (section "Voice input (STT)"). Related: https://latestn.com/tool/kiro/settings/environment-variables How do I set environment variables for Kiro Crew? https://latestn.com/tool/kiro/settings/experimental-settings-integration How do I configure experimental features in Kiro CLI settings? https://latestn.com/tool/kiro/settings/extension-registry-linux How do I set up a custom extension registry on Linux in Kiro? https://latestn.com/tool/kiro/settings/enable-todo-lists How do I enable TODO lists in Kiro CLI? https://latestn.com/tool/kiro/settings/enable-tool-search-v2 How do I enable Tool Search in Kiro V2 sessions? https://latestn.com/tool/kiro/settings/enable-tool-search-v3 How do I enable Tool Search in Kiro V3 settings? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T13:22:57Z | changed | key start default: — → on by default | [1] 2026-11-20T13:22:57Z | changed | silence finalization time: — → approximately 1.5 seconds | [1] 2026-11-20T13:22:57Z | changed | platform support: — → macOS desktop installs | [1] 2026-11-20T13:22:57Z | changed | base model download size: — → ~148 MB | [1] 2026-11-20T13:22:57Z | changed | cloud provider install command: pip install "kirocrew[voice]" → — | [1] 2026-11-20T13:22:57Z | changed | silence finalization: approximately 1.5 seconds → — | [1] 2026-11-20T13:22:57Z | changed | default model download size: ~148 MB → — | [1] 2026-11-13T03:38:27Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/kiro/settings/enable-voice-input-stt/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/kiro/settings/enable-voice-input-stt POST: https://latestn.com/dispute/tool/kiro/settings/enable-voice-input-stt with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/kiro/settings/enable-voice-input-stt?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I enable voice input (speech-to-text) in Kiro Crew chat? Revision 2, last verified 2026-11-20T13:22:57Z. https://latestn.com/tool/kiro/settings/enable-voice-input-stt (accessed 2026-11-21T09:58:12Z). @misc{LatestN_tool_kiro_settings_enable_voice_input_stt_r2, title = {How do I enable voice input (speech-to-text) in Kiro Crew chat?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/kiro/settings/enable-voice-input-stt}}, note = {Revision 2; digest sha256:e21ac9fbf63bd6bb; last verified 2026-11-20T13:22:57Z; accessed 2026-11-21T09:58:12Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/kiro/settings/enable-voice-input-stt