Mispher：集听写、重写、翻译与本地 Agent 于一体的 Mac 工具

大家好，Product Hunt 👋 每个听写应用都给你文本。Mispher 则给你真正想要的：文本、改写后的段落、翻译好的句子，或者一个去执行操作的 Agent。全代理式转录，完全在你的 Mac 上运行。无需账户，无需遥测。

网站：https://mispher.com

代码：https://github.com/dsaad68/mispher

按住左 ⌥ 键，拨动环形转盘，松开后选择要执行的操作：

• 转写：将干净文本放入任何具有焦点的输入框。
• 原地重写：在任意应用中高亮一个句子，按住按键，说出“将此句改短”，它便就地替换所选内容。
• 翻译：说出一种语言，插入另一种语言。
• Ask：一个本地 LFM2.5 Agent，可规划、调用工具（Apple Notes、剪贴板、文件），并通过 HTTP 或 stdio 连接到你自己的 MCP 服务器，需要时支持 OAuth。写入操作受限于你为每个工具设置的批准卡片。

全程无 Whisper，也无需 API 密钥。提供五种识别器，可按语言选择：Parakeet EOU 实时流式识别英语，Nemotron 流式支持约 40 种语言，Parakeet TDT 覆盖 25 种欧洲语言，Parakeet CTC 或 Qwen3-ASR 处理中文。其中四种运行在神经引擎上，Qwen3-ASR 则对接本地的 llama-server。规划器与视觉模型均采用 MLX。

一切都可定制。你可以重新映射转盘的每一个分区。为每种模式指定独立的快捷键，并为每个快捷键赋予不同的交互方式：按下说话、点按开关，或长按后转为免提模式，停下说话即结束。为它添加自定义词典，确保你的姓名和术语正确识别。决定松开按键后是直接提交文本还是暂存。选择录音界面的显示方式：从刘海区域弹出的灵动岛、下方的药丸状指示器、可拖拽面板或完整窗口。

你也可以完全掌控 Agent。每个工具和每个 MCP 服务器都可设定三种策略之一：批准则立即执行，询问则在批准卡片前等待你确认，拒绝则模型仍可感知该工具但绝不运行。完全停用某个工具后，它将从 Agent 的世界中消失。可随时为任一模式更换底层模型。打开 Agent 的视觉能力，或让规划器保持盲态。

即将到来：Gemma 4 E4B、Qwen3.6 27B/35B 以及 Ornith 1.0。Ornith 特别值得关注，它是一个单一的 9B 检查点，同时驱动规划器并支持视觉子代理，这样需要屏幕感知的 Ask 功能就无需再下载第二个模型。

它免费且基于 MIT 协议。安装命令：brew install --cask dsaad68/tap/mispher，适用于 Apple Silicon、macOS 26。

• Daniel

Hey Product Hunt 👋 Every dictation app gives you text. Mispher gives you what you actually wanted: the text, or the paragraph rewritten, or the sentence translated, or an agent that went and did it. Agentic transcription, entirely on your Mac. No account, no telemetry. Site:

https://mispher.com

Code:

https://github.com/dsaad68/mispher

Hold left ⌥, flick the radial dial, and pick what happens when you let go: - Transcribe drops clean text into whatever field has focus. - Rewrite in place: highlight a sentence in any app, hold the key, say "make this shorter," and it swaps the selection where it sits. - Translate: speak one language, insert another. - Ask: a local LFM2.5 agent that plans, calls tools (Apple Notes, clipboard, files), and connects to your own MCP servers over HTTP or stdio, with OAuth when a server needs it. Writes are gated behind an approval card you set per tool. No Whisper anywhere, and no API key. Five recognizers, and you pick per language: Parakeet EOU streams English live, Nemotron streams ~40 languages, Parakeet TDT covers 25 European ones, and Parakeet CTC or Qwen3-ASR take Mandarin. Four run on the Neural Engine, Qwen3-ASR against a llama-server on localhost. The planner and vision models are MLX. Nothing about it is fixed. Remap every slice of the dial. Give each mode its own shortcut, and each shortcut its own feel: push-to-talk, tap-on-tap-off, or a long-press that goes hands-free and stops when you do. Teach it a custom dictionary so your names and jargon come out right. Decide whether releasing the key commits the text or parks it. Pick how recording appears: a Dynamic Island out of the notch, a pill under it, a draggable panel, or the full window. The agent is yours to govern too. Every tool and every MCP server gets one of three policies: approve and it runs, ask and it waits for you at an approval card, deny and the model can still see the tool but never runs it. Deactivate one entirely and it vanishes from the agent's world. Swap the model behind any mode. Turn the agent's vision on, or leave the planner blind. Coming next: Gemma 4 E4B, Qwen3.6 27B/35B, and Ornith 1.0. Ornith is the interesting one, a single 9B checkpoint that drives the planner and backs the vision subagent, so screen-aware Ask stops needing a second model download. It's free and MIT. Install with: brew install --cask dsaad68/tap/mispher Apple Silicon, macOS 26. - Daniel