MimoTtsAsr26Free：MiMo TTS 的工程化封装与语音工作流
MimoTtsAsr26Free（@user_168d274d/mimofreetts，v2.9.1）是 SkillHub 社区 Skill，在官方 MiMo V2.5 TTS API 之上提供脚本化工程能力：三合一 TTS 调用、无 Key 时 edge-tts 降级、120 字分句、缓存与 502/503/超时重试、文本预处理与合成质检，并支持 --file 批量、-o 格式推断、--recommend-voice、--watch 目录监听及 asr.py 与 TTS+ASR 示例。需 API Key 时标签为 requires_api_key=true。本文说明定位、能力与 skillhub install 安装方式，细节以 SKILL.md 为准。
Read MoreTencentCloud ASR：在 Agent 中接入腾讯云语音转文字
TencentCloud ASR（@tencent-adm/tencentcloud-asr，v0.1.5）由腾讯云语音团队在 SkillHub 发布，需配置 API Key，支持本地文件与 URL 音频。提供一句话识别（≤60s）、录音识别极速版（≤2h/100MB 同步）与录音识别（≤5h 异步）三种模式，适用于转写、字幕、会议与语音消息等场景。本文介绍定位、能力、SkillHub 安装提示与使用注意，并给出官方地址。
Read Morexby-asr-5: DeepSeek Harness Speech Recognition Plugin
xby-skill/xby-asr-5 is a DeepSeek Harness (DSH) plugin for integrating speech recognition capabilities. It supports five languages: Chinese, English, Japanese, Korean, and Cantonese, with automatic language detection. Core features include setting the API key and recognizing audio URLs, Base64-encoded data, and local files. Users must first register on the Xiaobenyang official website to obtain an API key for authentication, and then invoke the recognition service through the corresponding function. The plugin source is hosted on GitHub and is licensed under the MIT License.
Read Moredsh-voice-input: DeepSeek Harness Voice Input Plugin
`dsh-voice-input` is a voice input plugin for DeepSeek Harness that converts speech to text using browser native APIs or an OpenAI-compatible `/audio/transcriptions` endpoint. The plugin integrates a microphone button into the input field, supports real-time status feedback, engine selection (browser, cloud, or local), and secure credential management. It is zero-dependency, requires no build steps, and provides one-click install and uninstall scripts, with support for Whisper local services and Ollama (models with audio projection capabilities).
Read MoreDeepSeek Harness Plugin: dsh-bili-asr
The DeepSeek Harness plugin `dsh-bili-asr` parses Bilibili videos and extracts text. It preferentially reads built-in subtitles and falls back to a local Whisper model for speech-to-text transcription when subtitles are unavailable, returning timestamped text with export support for SRT, TXT, and JSON. The tool supports multiple link formats, is compatible with Windows/macOS/Linux, and automatically registers as a host tool. An ffmpeg dependency is required for installation; the model must be downloaded on first use. It supports CPU/GPU acceleration and is licensed under the MIT License.
Read More