AI Skill Hub 推荐使用:Heard语音编程助手 是一款优质的Agent工作流。AI 综合评分 7.2 分,在同类工具中表现稳健。如果你正在寻找可靠的Agent工作流解决方案,这是一个值得深入了解的选择。
Heard语音编程助手 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Heard语音编程助手 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:pip 安装(推荐)
pip install heard
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install heard
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/heardlabs/heard
cd heard
pip install -e .
# 验证安装
python -c "import heard; print('安装成功')"
# 命令行使用
heard --help
# 基本用法
heard input_file -o output_file
# Python 代码中调用
import heard
# 示例
result = heard.process("input")
print(result)
# heard 配置文件示例(config.yml) app: name: "heard" debug: false log_level: "INFO" # 运行时指定配置文件 heard --config config.yml # 或通过环境变量配置 export HEARD_API_KEY="your-key" export HEARD_OUTPUT_DIR="./output"
<p align="center"> <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/logo/heard-logo-dark.svg"> <img alt="Heard" src="docs/assets/logo/heard-logo-light.svg" width="360"> </picture> </p>
<p align="center"> Heard speaks your coding agent's outputs so you can get up, walk around, and still know what's going on. </p>
<p align="center"> <sub>Counterpart to input tools like <a href="https://wisprflow.ai">Wispr Flow</a>. Wispr handles what you say <i>to</i> your agent; Heard handles what it says back.</sub> </p>
<p align="center"> <a href="https://github.com/heardlabs/heard/releases/latest"><img src="https://img.shields.io/github/v/release/heardlabs/heard?label=release&color=0aa" alt="Latest release"></a> <a href="https://github.com/heardlabs/heard/blob/main/LICENSE"><img src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" alt="License: Apache-2.0"></a> <a href="https://github.com/heardlabs/heard"><img src="https://img.shields.io/github/stars/heardlabs/heard?style=social" alt="GitHub stars"></a> </p>
<p align="center"> <a href="https://heard.dev">heard.dev</a> · <a href="https://github.com/heardlabs/heard/releases/latest">Releases</a> · <a href="https://github.com/heardlabs/heard/issues">Issues</a> </p>
<br/>
Bring an ElevenLabs key for the best voices, or use Kokoro — free, local, no key.
Paste this into Claude Code, Codex, or any AI coding tool:
Install Heard so you narrate your responses to me. Run: curl -L https://github.com/heardlabs/heard/releases/latest/download/Heard.zip -o /tmp/heard.zip && unzip -o /tmp/heard.zip -d /Applications && open /Applications/Heard.app — a window will pop up and I'll fill it in.
<details> <summary><b>Does my agent's output leave my machine?</b></summary>
Depends on which backends you opt into.
- Voice synth. ElevenLabs sends spoken text over HTTPS. Kokoro runs fully locally — nothing leaves the machine. - 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. - Telemetry. None. No analytics, no crash reporters, no phone-home. </details>
<details> <summary><b>What does ElevenLabs actually cost in practice?</b></summary>
The 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. </details>
<details> <summary><b>Will narration slow down my agent?</b></summary>
No. Hooks fire-and-forget over a Unix socket; the daemon synthesises and plays asynchronously. Your agent never blocks on Heard. </details>
<details> <summary><b>Is this open source? How do I contribute?</b></summary>
Yes — Apache 2.0. The easiest places to contribute are adapters (heard/adapters/), personas (heard/personas/*.md), and verbosity profiles (heard/profiles/*.yaml). </details>
创新的语音交互方案,有效降低编程过程中的认知负荷,但生态支持度有限,需进一步优化代理兼容性。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ Apache 2.0 — 宽松开源协议,可商用,需保留版权声明和 NOTICE 文件,含专利授权条款。
总体来看,Heard语音编程助手 是一款质量良好的Agent工作流,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | heard |
| 原始描述 | 开源AI工作流:A voice companion for AI coding agents. Speaks your agent's replies so you can k。⭐109 · Python |
| Topics | 语音交互AI代理编程工具工作流自动化 |
| GitHub | https://github.com/heardlabs/heard |
| License | Apache-2.0 |
| 语言 | Python |
收录时间:2026-05-25 · 更新时间:2026-05-30 · License:Apache-2.0 · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端