[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2379":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":13,"stars90d":14,"forks30d":14,"starsTrendScore":17,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":20,"hasPages":20,"topics":22,"createdAt":9,"pushedAt":9,"updatedAt":23,"readmeContent":24,"aiSummary":25,"trendingCount":14,"starSnapshotCount":14,"syncStatus":26,"lastSyncTime":27,"discoverSource":28},2379,"heard","heardlabs\u002Fheard","heardlabs","A voice companion for AI coding agents. Speaks your agent's replies so you can keep working.",null,"Python",114,14,8,0,3,5,9,52.83,"Apache License 2.0",false,"main",[],"2026-06-12 04:00:14","\u003Cp align=\"center\">\n  \u003Cpicture>\n    \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs\u002Fassets\u002Flogo\u002Fheard-logo-dark.svg\">\n    \u003Cimg alt=\"Heard\" src=\"docs\u002Fassets\u002Flogo\u002Fheard-logo-light.svg\" width=\"360\">\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\n\n\u003Ch2 align=\"center\">Your coding agent has a voice now.\u003C\u002Fh2>\n\n\u003Cp align=\"center\">\n  Heard speaks your coding agent's outputs so you can get up, walk around, and still know what's going on.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Csub>Counterpart to input tools like \u003Ca href=\"https:\u002F\u002Fwisprflow.ai\">Wispr Flow\u003C\u002Fa>. Wispr handles what you say \u003Ci>to\u003C\u002Fi> your agent; Heard handles what it says back.\u003C\u002Fsub>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\u002Freleases\u002Flatest\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fheardlabs\u002Fheard?label=release&color=0aa\" alt=\"Latest release\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\u002Fblob\u002Fmain\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202.0-blue.svg\" alt=\"License: Apache-2.0\">\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fheardlabs\u002Fheard?style=social\" alt=\"GitHub stars\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fheard.dev\">heard.dev\u003C\u002Fa>\n   · \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\u002Freleases\u002Flatest\">Releases\u003C\u002Fa>\n   · \n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\u002Fissues\">Issues\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cbr\u002F>\n\n## See and hear it run\n🔊 Turn sound on for demo\n\nhttps:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fd823a946-fb6f-438b-904f-aa66d4268ed1\n\n## Install\n\nBring an [ElevenLabs](https:\u002F\u002Felevenlabs.io) key for the best voices, or use **Kokoro** — free, local, no key.\n\n### Have your coding tool install it (recommended)\n\nPaste this into Claude Code, Codex, or any AI coding tool:\n\n> Install Heard so you narrate your responses to me. Run: `curl -L https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\u002Freleases\u002Flatest\u002Fdownload\u002FHeard.zip -o \u002Ftmp\u002Fheard.zip && unzip -o \u002Ftmp\u002Fheard.zip -d \u002FApplications && open \u002FApplications\u002FHeard.app` — a window will pop up and I'll fill it in.\n\n### Manual\n\nDownload the latest [`Heard.zip`](https:\u002F\u002Fgithub.com\u002Fheardlabs\u002Fheard\u002Freleases\u002Flatest\u002Fdownload\u002FHeard.zip), drag `Heard.app` into `\u002FApplications`, double-click to launch. Onboarding walks you through voice \u002F API key \u002F hotkey \u002F which agents to wire up.\n\n## What it does\n\n- **Narrates tool calls + intermediate prose**, not just final summaries. \"Looking at your test failures.\" \"Three failures in auth.py.\"\n- **Multi-agent aware.** Run 3+ agents in parallel; Heard auto-routes narration in distinct voices so you can actually follow the work.\n- **Four personas, fork-your-own.** Aria (calm, direct), Friday (bright, breezy), Jarvis (Marvel butler), Atlas (cinematic narrator).\n- **Works with any coding CLI.** First-class adapters for Claude Code + Codex; `heard run \u003Ccommand>` wraps anything else.\n\n## Personas\n\n| Persona | Vibe |\n|---|---|\n| **aria** | Calm, direct, never editorial. Senior pair-programmer. |\n| **friday** | Bright, breezy, three steps ahead. Sprinkles \"boss\". |\n| **jarvis** | Marvel JARVIS-coded butler. Dry wit, \"Sir\" only on summaries. |\n| **atlas** | Cinematic narrator. Greek tragedy applied to compile cycles. |\n\n[▶ Hear the voices in action on heard.dev →](https:\u002F\u002Fheard.dev\u002F#voices)\n\nFork your own — drop a Markdown file with frontmatter into `~\u002FLibrary\u002FApplication Support\u002Fheard\u002Fpersonas\u002F`.\n\n## Running multiple agents\n\nHeard auto-detects 2+ concurrent sessions and shifts mode.\n\n| Mode | When | What you hear |\n|---|---|---|\n| **Solo** | One session active | Full narration in your persona's voice. |\n| **Swarm** | 2+ sessions concurrent | Most-recent session narrates; background agents pierce only on failures and questions, with a periodic digest. Each gets a distinct voice. |\n| **Pinned** | You picked one in the menu | Focus locks to that session. |\n\n## Tuning\n\nFour verbosity profiles (`quiet` → `brief` → `normal` → `verbose`), tunable globally or per-repo via `.heard.yaml`. Failures and wait-state questions always pierce.\n\nEveryday commands:\n\n```bash\nheard preset jarvis              # switch persona\nheard config set verbosity brief # quieter\nheard pause                      # or ⇧⌥. to stop narrating\nheard continue                   # or ⇧⌥, to resume\nheard doctor                     # end-to-end self-test\n```\n\n## FAQ\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>Does my agent's output leave my machine?\u003C\u002Fb>\u003C\u002Fsummary>\n\nDepends on which backends you opt into.\n\n- **Voice synth.** ElevenLabs sends spoken text over HTTPS. **Kokoro** runs fully locally — nothing leaves the machine.\n- **Persona rewrites.** If you provide an Anthropic key, Heard sends short candidate lines to Claude Haiku 4.5 to rewrite in-character. Skip the key and Heard uses neutral templates locally.\n- **Telemetry.** None. No analytics, no crash reporters, no phone-home.\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>What does ElevenLabs actually cost in practice?\u003C\u002Fb>\u003C\u002Fsummary>\n\nThe free tier covers light daily use. A heavy day of pair-programming (2-3 hrs of narration) typically lands in the **few-cents-to-low-dimes** range on the paid Starter plan. Switch to **Kokoro** (free, local) for a hard ceiling.\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>Will narration slow down my agent?\u003C\u002Fb>\u003C\u002Fsummary>\n\nNo. Hooks fire-and-forget over a Unix socket; the daemon synthesises and plays asynchronously. Your agent never blocks on Heard.\n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>\u003Cb>Is this open source? How do I contribute?\u003C\u002Fb>\u003C\u002Fsummary>\n\nYes — Apache 2.0. The easiest places to contribute are adapters (`heard\u002Fadapters\u002F`), personas (`heard\u002Fpersonas\u002F*.md`), and verbosity profiles (`heard\u002Fprofiles\u002F*.yaml`).\n\u003C\u002Fdetails>\n\n## Compatibility\n\nmacOS 13+ · Claude Code + Codex first-class · Cursor and Aider planned · anything else via `heard run`.\n\n## Status\n\nv0.4 — multi-agent routing, profile-based verbosity, automatic ElevenLabs ⇄ Kokoro failover. Used daily by the author. APIs may still change before v1.\n\n## License\n\nApache 2.0.\n","Heard 是一个为AI编码助手提供语音输出的伴侣工具，能够将编码助手的回复以语音形式读出，使开发者即使在走动时也能了解代码进展。其核心功能包括叙述工具调用和中间过程、支持多代理同时运行并自动区分声音以及提供四种不同风格的人格化声音选项。技术上，Heard 使用Python编写，并且可以通过ElevenLabs或内置免费的Kokoro服务来实现高质量的语音合成。此项目特别适合于需要长时间编码但又希望保持活动状态的开发者使用，或是任何希望通过听觉方式接收信息以提高工作效率的情境。",2,"2026-06-11 02:49:40","CREATED_QUERY"]