dsh-speak: Using macOS to Read Text Aloud in DeepSeek Harness
dsh-speak is a macOS plugin designed for DeepSeek Harness, leveraging the system `say` command to provide local text-to-speech functionality. It offers Agent tool invocation, message button read-aloud, and selected-text read-aloud features, with automatic detection for Chinese, English, Japanese, and Korean, along with personalized settings. Installation can be done via the plugin manager, CLI, or manual configuration. The plugin operates without network transmission, making it suitable for debugging, validation, and interactive experiences, but it is limited to DSH 0.2.x and macOS.
Read Moredsh-speak: Adding Voice Broadcast to DSH and Other AI Coding Harnesses
dsh-speak is a DSH web plugin maintained by Alan2Z, designed to address the pain point of users missing screen prompts during long tasks. It utilizes system speech synthesis technology to read aloud in real-time the final responses, approval requests, and agent queries from DSH sessions. The plugin supports both Windows (SAPI5) and macOS (say command), prioritizes natural speech, and includes automatic cleaning of Markdown, URLs, and emojis to adapt to speech synthesis. Its core features include: monitoring event streams and broadcasting key information, a best-effort operating mode (non-blocking, no exceptions thrown), and the Bundle auto-registration feature introduced in version 1.3.0, which simplifies installation and configuration. The installation is flexible, supporting npm or gi...
Read More