Answer: Run /voice, which detects that no model is present, then confirm the download in the panel by pressing y (or pass --confirm-download on the CLI command in headless or piped invocations). The model is cached under ~/.cache/kiro/models/. Status: Confirmed Entry: tool/kiro/install-and-setup/download-speech-model Revision: 2 Digest: sha256:57689ce789779f4d (changes whenever the content changes) Timeline: Created: 2026-11-13T03:37:22Z Last changed: 2026-11-20T13:21:14Z (model size: — → about 148 MB) Last verified: 2026-11-20T13:21:14Z Next check: 2026-11-21T13:21:14Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Unit | Source | As of command to run | /voice | | [1] | 2026-11-20 confirmation key | y | | [1] | 2026-11-20 model size | about 148 MB | MB | [1] | 2026-11-20 license | MIT | | [1] | 2026-11-20 cache location | ~/.cache/kiro/models/ | | [1] | 2026-11-20 headless flag | --confirm-download | | [1] | 2026-11-20 Sources: [1] Amazon Web Services. "Voice mode - CLI - Docs - Kiro". https://kiro.dev/docs/cli/voice/ Role: primary. Accessed: 2026-11-20T13:21:14Z Quote: "Run /voice The command detects that no model is present." (Supports: command to run) Quote: "Press y to download or n to cancel." (Supports: confirmation key) Quote: "its size (about 148 MB for the default base model)" (Supports: model size) Quote: "and its license (MIT)" (Supports: license) Quote: "The model is cached under ~/.cache/kiro/models/ ." (Supports: cache location) Quote: "Pass --confirm-download on the CLI command directly to approve the one-time download." (Supports: headless flag) Published: 2026-11-20T07:39:25Z Snapshot SHA-256: 1a6a6ba716e4d347629cb04ec5d73634616160eff17dd3105f4bf72e70963449 (captured 2026-11-20T13:21:14Z) 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 2026-11-20T13:21:14Z. No independent second source is configured for this entry Last successful check: 2026-11-20T13:21:14Z Last attempt: 2026-11-20T13:21:14Z Notes and limitations: Extracted automatically from a single official source (section "First run: downloading the speech model"). Related: https://latestn.com/tool/kiro/install-and-setup/first-project-prerequisites What are the prerequisites for starting a first project in Kiro? https://latestn.com/tool/kiro/install-and-setup/first-task-web How do I start my first task in Kiro Web? https://latestn.com/tool/kiro/install-and-setup/first-time-setup How do I set up Kiro Crew for the first time using the kirocrew CLI? https://latestn.com/tool/kiro/install-and-setup/deploy-cognito-and-bootstrap-db How do I deploy the Cognito User Pool and bootstrap the database for the Kiro game? https://latestn.com/tool/kiro/install-and-setup/downgrade-ide-1-0 How do I downgrade from Kiro IDE 1.0? https://latestn.com/tool/kiro/install-and-setup/downgrade-version How do I downgrade Kiro to a previous version? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-20T13:21:14Z | changed | model size: — → about 148 MB | [1] 2026-11-20T13:21:14Z | changed | confirmation key: — → y | [1] 2026-11-20T13:21:14Z | changed | command to run: — → /voice | [1] 2026-11-20T13:21:14Z | changed | confirm key: y → — | [1] 2026-11-20T13:21:14Z | changed | default model size: about 148 MB → — | [1] 2026-11-20T13:21:14Z | changed | command: /voice → — | [1] 2026-11-13T03:37:22Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/kiro/install-and-setup/download-speech-model/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/install-and-setup/download-speech-model POST: https://latestn.com/dispute/tool/kiro/install-and-setup/download-speech-model with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/kiro/install-and-setup/download-speech-model?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I download the speech model for Kiro CLI voice mode on first run? Revision 2, last verified 2026-11-20T13:21:14Z. https://latestn.com/tool/kiro/install-and-setup/download-speech-model (accessed 2026-11-21T10:04:16Z). @misc{LatestN_tool_kiro_install_and_setup_download_speech_model_r2, title = {How do I download the speech model for Kiro CLI voice mode on first run?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/kiro/install-and-setup/download-speech-model}}, note = {Revision 2; digest sha256:57689ce789779f4d; last verified 2026-11-20T13:21:14Z; accessed 2026-11-21T10:04:16Z} } 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/install-and-setup/download-speech-model