moss-transcribe-diarize

Comprehensive MOSS Transcribe Diarize workflow for high-confidence multi-speaker ASR. Use when users need (1) timestamped transcription, (2) speaker-labeled segments/diarization, (3) meeting or interview transcript extraction, or (4) ASR from URL/Base64/local audio-video files with structured post-processing outputs (raw JSON, segment timeline, and by-speaker summary).

View Source SKILL.md

Stars

Installs

Status

ACTIVE

Visibility

PUBLIC

安装方式

直接复制以下提示词，发送给你的 AI 助手即可完成安装。

请先检查是否已安装 SkillHub 商店，若未安装，请根据 https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/skillhub.md 安装 SkillHub 商店，然后安装 moss-transcribe-diarize 技能。若已安装，则直接安装 moss-transcribe-diarize 技能。

Overview

Skill Key: helloeveryworlds/moss-transcribe-diarize
Author: helloeveryworlds
Source Repo: openclaw/skills
Version: -
Source Path: skills/helloeveryworlds/moss-transcribe-diarize
Latest Commit SHA: ea4b2efd4c14759a05c98dfa9762b861a57503d1

Extracted Content

SKILL.md excerpt

# MOSS Transcribe Diarize Skill

Call this skill when users want:
- 多人语音转写（带说话人）
- 带时间戳的会议纪要原文
- 从音视频 URL / 本地文件做 ASR + diarization

## Quick workflow

1. 准备音频来源（URL / 本地文件 / Base64）
2. 调用 `scripts/transcribe.py`
3. 用 `segments` 生成：逐段文本、按说话人汇总、会后纪要

## API assumptions (from docs page)
- 模型名固定：`moss-transcribe-diarize`
- 请求体核心字段：
  - `audio_data`（URL 或 data URL）
  - `model`
  - `sampling_params`（如 `max_new_tokens`, `temperature`）
  - `meta_info`（可选）
- 返回中重点看：
  - `text`
  - `meta_info`
  - `segments`（含时间戳、speaker、content）

> 官方文档入口：`https://studio.mosi.cn/docs/moss-transcribe-diarize`

## Run

```bash
# URL 音频
python scripts/transcribe.py \
  --audio-url "https://example.com/audio.mp3" \
  --api-key "$MOSS_API_KEY" \
  --out result.json

# 本地文件（自动转 data URL）
python scripts/transcribe.py \
  --file "/path/to/meeting.mp4" \
  --api-key "$MOSS_API_KEY" \
  --out result.json
```

## Endpoint

默认 endpoint：`https://studio.mosi.cn/v1/audio/transcriptions`

如果你的环境 endpoint 不同，用参数覆盖：

```bash
--endpoint "https://your-endpoint"
```

## Output handling

- 原始结果保存为 JSON
- 脚本会额外导出：
  - `*.segments.txt`（逐段）
  - `*.by_speaker.txt`（按说话人）

Related Claw Skills

openstockdata

stock-data-skill

★ 4

OpenClaw Skill for stock data analysis

capt-marbles

geo-optimization

★ 1

Generative Engine Optimization (GEO) for AI search visibility. Optimize content to appear in ChatGPT, Perplexity, Claude, and Google AI Overviews. Use when optimizing websites, pages, or content for LLM discoverability and citation.

capgoblin

credex-protocol

★ 0

Access unsecured credit lines for AI agents on the Arc Network using the Credex Protocol. Use for borrowing USDC against reputation, repaying debt to grow credit limits, providing liquidity as an LP, or managing cross-chain USDC via Circle Bridge. Triggers on "borrow from credex", "repay debt", "deposit to pool", "check credit status", "provide liquidity", or any credit/lending task on Arc.

capt-marbles

phantombuster

★ 0

Control PhantomBuster automation agents via API. List agents, launch automations, get output/results, check status, and abort running agents. Use when the user needs to run LinkedIn scraping, Twitter automation, lead generation phantoms, or any PhantomBuster workflow.

camelsprout

duckdb-en

★ 0

DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV/Parquet/JSON analysis, database queries, or data conversion. Triggers on "duckdb", "sql", "query", "data analysis", "parquet", "convert data".

camohiddendj

ddg-search

★ 0

DuckDuckGo HTML search scraper CLI with JSON, CSV, OpenSearch, markdown, and compact outputs.

Analysis Signals

Dependencies

python