{"id":44318763,"url":"https://github.com/yukukotani/pi-voice","last_synced_at":"2026-02-15T10:01:28.722Z","repository":{"id":337672605,"uuid":"1152876007","full_name":"yukukotani/pi-voice","owner":"yukukotani","description":"Headless voice interface for the Pi Coding Agent","archived":false,"fork":false,"pushed_at":"2026-02-11T04:21:32.000Z","size":540,"stargazers_count":43,"open_issues_count":2,"forks_count":3,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-12T14:56:46.036Z","etag":null,"topics":["pi","voice-ai"],"latest_commit_sha":null,"homepage":"","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yukukotani.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2026-02-08T15:18:25.000Z","updated_at":"2026-02-11T20:42:19.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/yukukotani/pi-voice","commit_stats":null,"previous_names":["yukukotani/pi-voice"],"tags_count":4,"template":false,"template_full_name":null,"purl":"pkg:github/yukukotani/pi-voice","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yukukotani%2Fpi-voice","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yukukotani%2Fpi-voice/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yukukotani%2Fpi-voice/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yukukotani%2Fpi-voice/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yukukotani","download_url":"https://codeload.github.com/yukukotani/pi-voice/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yukukotani%2Fpi-voice/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29441082,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-14T07:24:13.446Z","status":"ssl_error","status_checked_at":"2026-02-14T07:23:58.969Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["pi","voice-ai"],"created_at":"2026-02-11T06:05:12.806Z","updated_at":"2026-02-14T09:01:18.390Z","avatar_url":"https://github.com/yukukotani.png","language":"TypeScript","funding_links":[],"categories":["Extensions"],"sub_categories":[],"readme":"# pi-voice\n\nHeadless voice interface for the [Pi Coding Agent](https://github.com/badlogic/pi-mono). Hold a key, speak, and pi executes your instructions with voice feedback.\n\n#### Demo using ElevenLabs provider (make sure unmuted)\n\nhttps://github.com/user-attachments/assets/76adb941-83cf-4394-b8d2-f6d73a1df8bc\n\n## Installation\n\n```bash\nnpm i -g pi-voice\n# or\nbun i -g pi-voice\n```\n\n## Usage\n\npi-voice is a daemon-style application that runs in the background once started. You can push-to-talk with the agent.\n\n```bash\npi-voice start    # start the daemon in the background\npi-voice status   # show state, PID, and uptime\npi-voice stop     # stop the daemon\n```\n\nThe push-to-talk trigger defaults to `Cmd+Shift+I` (macOS) / `Win+Shift+I` (Windows). Hold the key to record, release to send.\n\n## Setting\n\n### pi agent configuration\n\npi-voice launches a Pi agent session with the directory where `pi-voice start` was executed. This means **all standard pi configuration works as-is**:\n\n- `AGENTS.md` — walked up from `cwd` to the filesystem root\n- `.pi/settings.json` — project-level settings\n- `.pi/skills/`, `.pi/extensions/`, `.pi/prompts/` — project-level resources\n- `~/.pi/agent/` — global settings, skills, extensions, prompts, and models\n- and more\n\nRefer to the [Pi documentation](https://github.com/badlogic/pi-mono/tree/main/packages/coding-agent) for details on these settings.\n\n### pi-voice configuration\n\nYou can configure pi-voice in `.pi/pi-voice.json`:\n\n```json\n{\n  \"key\": \"ctrl+t\",\n  \"provider\": \"local\"\n}\n```\n\n| Key | Description |\n| --- | --- |\n| `key` | Push-to-talk shortcut. Combine modifiers (`ctrl`, `shift`, `alt`/`opt`, `meta`/`cmd`) and a main key with `+`. Examples: `\"ctrl+t\"`, `\"alt+space\"`, `\"ctrl+shift+r\"`. Default: `\"meta+shift+i\"`. |\n| `provider` | Speech provider for STT \u0026 TTS. `\"local\"`, `\"gemini\"` (Vertex AI or Gemini API), `\"openai\"`, or `\"elevenlabs\"`. Default: `\"local\"`. |\n\n### Environment variables\n\n| Provider | Required variables |\n| --- | --- |\n| `local` | None (model is auto-downloaded on first launch). Optional: `WHISPER_MODEL_PATH` (custom model path), `WHISPER_MODEL` (model name, default `medium-q5_0`), `SAY_VOICE` (macOS `say` voice name, e.g. `\"Kyoko\"`). |\n| `gemini` | **Vertex AI:** `GOOGLE_CLOUD_PROJECT`, `GOOGLE_CLOUD_LOCATION` (optional, default `us-central1`). **Gemini API:** `GEMINI_API_KEY` or `GOOGLE_API_KEY`. If `GOOGLE_CLOUD_PROJECT` is set, Vertex AI is used; set `GOOGLE_GENAI_USE_VERTEXAI=false` to force API key mode. |\n| `openai` | `OPENAI_API_KEY` |\n| `elevenlabs` | `ELEVENLABS_API_KEY`. Optional: `ELEVENLABS_VOICE_ID` (TTS voice, default `CwhRBWXzGAHq8TQ4Fs17`), `ELEVENLABS_TTS_MODEL` (default `eleven_flash_v2_5`). |\n\n#### Logging\n\nThe daemon writes structured JSON logs to both the console and a log file. The default log file path is `$XDG_CONFIG_HOME/pi-voice/daemon.log` (falls back to `~/.config/pi-voice/daemon.log`).\n\nTo override the log file path:\n\n```bash\nexport PI_VOICE_LOG_PATH=/path/to/custom.log\n```\n\n#### Whisper model (local provider)\n\nThe `local` provider uses [Whisper](https://github.com/openai/whisper) for STT and the macOS `say` command for TTS. On first launch, a ggml-format Whisper model (`medium-q5_0`, ~514 MB) is automatically downloaded to `~/.pi-agent/whisper/` and cached for subsequent runs.\n\nTo use a different model, set `WHISPER_MODEL`:\n\n```bash\nexport WHISPER_MODEL=base     # smaller \u0026 faster\n```\n\nOr point to your own model file directly:\n\n```bash\nexport WHISPER_MODEL_PATH=/path/to/ggml-custom.bin\n```\n\n## Contributing\n\nSee [CONTRIBUTING.md](CONTRIBUTING.md) for development setup, build commands, and release workflow.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyukukotani%2Fpi-voice","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyukukotani%2Fpi-voice","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyukukotani%2Fpi-voice/lists"}