auralwise_cli 1.0.1 → 1.0.3

package/README.md

@@ -0,0 +1,257 @@
+# AuralWise CLI
+
+[中文文档](./README_CN.md)
+
+Command-line interface for [AuralWise](https://auralwise.cn) Speech Intelligence API.
+
+One API call returns transcription, speaker diarization, speaker embeddings, word-level timestamps, and 521-class audio event detection — all at once.
+
+## Features
+
+- **Speech Transcription** — 99 languages, with a dedicated Chinese engine (`optimize_zh`) for faster speed and higher accuracy
+- **Speaker Diarization** — Automatic speaker count detection, per-segment speaker labels
+- **Speaker Embeddings** — 192-dim voice print vectors for cross-recording speaker matching
+- **Timestamps** — Word-level (~10ms) or segment-level (~100ms) precision
+- **Audio Event Detection** — 521 AudioSet sound event classes (applause, cough, music, keyboard, etc.)
+- **VAD** — Voice Activity Detection segments
+- **Batch Mode** — Half-price processing using off-peak GPU capacity, delivered within 24h
+
+## Installation
+
+```bash
+npm install -g auralwise_cli
+```
+
+Requires Node.js >= 18.
+
+## Quick Start
+
+```bash
+# Set your API key (get one at https://auralwise.cn)
+export AURALWISE_API_KEY=asr_xxxxxxxxxxxxxxxxxxxx
+
+# Transcribe from URL — waits for completion and prints results
+auralwise transcribe https://example.com/meeting.mp3
+
+# Transcribe a local file (auto base64 upload)
+auralwise transcribe ./recording.wav
+
+# Chinese optimization mode (faster, cheaper for Chinese audio)
+auralwise transcribe ./meeting.mp3 --optimize-zh --language zh
+
+# Submit without waiting
+auralwise transcribe https://example.com/audio.mp3 --no-wait
+
+# Get JSON output
+auralwise transcribe ./audio.mp3 --json --output result.json
+```
+
+## Commands
+
+### `auralwise transcribe <source>`
+
+Submit an audio file for processing. `<source>` can be an HTTP(S) URL or a local file path.
+
+**Input modes:**
+- **URL mode** — Pass an `https://...` URL; the GPU node downloads directly
+- **File mode** — Pass a local file path; the CLI reads and uploads as base64
+
+**Common options:**
+
+| Option | Description |
+|--------|-------------|
+| `--language <lang>` | ASR language code (`zh`, `en`, `ja`, ...) or auto-detect if omitted |
+| `--optimize-zh` | Use dedicated Chinese engine (faster, cheaper, segment-level timestamps) |
+| `--no-asr` | Disable transcription |
+| `--no-diarize` | Disable speaker diarization |
+| `--no-events` | Disable audio event detection |
+| `--hotwords <words>` | Boost recognition of specific words (comma-separated) |
+| `--num-speakers <n>` | Set fixed number of speakers |
+| `--max-speakers <n>` | Max speakers for auto-detection (default: 10) |
+| `--batch` | Use batch mode (half-price, 24h delivery) |
+| `--no-wait` | Return immediately after task creation |
+| `--json` | Output result as JSON |
+| `--output <file>` | Save result to file |
+| `--callback-url <url>` | Webhook URL for completion notification |
+
+**Advanced ASR options:**
+
+| Option | Description |
+|--------|-------------|
+| `--beam-size <n>` | Beam search width (default: 5) |
+| `--temperature <n>` | Decoding temperature (default: 0.0) |
+| `--initial-prompt <text>` | Guide transcription style |
+| `--vad-threshold <n>` | VAD sensitivity 0-1 (default: 0.35) |
+| `--events-threshold <n>` | Audio event confidence threshold (default: 0.3) |
+| `--events-classes <list>` | Only detect specific event classes |
+
+### `auralwise tasks`
+
+List your tasks with optional filtering.
+
+```bash
+auralwise tasks                          # List all tasks
+auralwise tasks --status done            # Only completed tasks
+auralwise tasks --page 2 --page-size 50  # Pagination
+auralwise tasks --json                   # JSON output
+```
+
+### `auralwise task <id>`
+
+Get details of a specific task.
+
+```bash
+auralwise task 550e8400-e29b-41d4-a716-446655440000
+auralwise task 550e8400-e29b-41d4-a716-446655440000 --json
+```
+
+### `auralwise result <id>`
+
+Retrieve the full result of a completed task.
+
+```bash
+auralwise result <task-id>                     # Pretty-printed output
+auralwise result <task-id> --json              # JSON output
+auralwise result <task-id> --output result.json  # Save to file
+```
+
+### `auralwise delete <id>`
+
+Delete a task and its associated files.
+
+```bash
+auralwise delete <task-id>           # With confirmation prompt
+auralwise delete <task-id> --force   # Skip confirmation
+```
+
+### `auralwise events`
+
+Browse the 521 AudioSet sound event classes.
+
+```bash
+auralwise events                       # List all 521 classes
+auralwise events --search Cough        # Search by name
+auralwise events --category Music      # Filter by category
+auralwise events --json                # JSON output
+```
+
+## Configuration
+
+### API Key
+
+Set your API key via `--api-key` flag or environment variable:
+
+```bash
+# Environment variable (recommended)
+export AURALWISE_API_KEY=asr_xxxxxxxxxxxxxxxxxxxx
+
+# Or pass directly
+auralwise --api-key asr_xxxx transcribe ./audio.mp3
+```
+
+### Base URL
+
+Override the API endpoint (default: `https://auralwise.cn/api/v1`):
+
+```bash
+auralwise --base-url https://your-private-instance.com/api/v1 transcribe ./audio.mp3
+```
+
+### Language
+
+The CLI supports English and Chinese interfaces:
+
+```bash
+auralwise --locale zh --help           # Chinese interface
+auralwise --locale en transcribe --help  # English interface (default)
+```
+
+## Examples
+
+### Meeting transcription with speaker diarization
+
+```bash
+auralwise transcribe ./meeting.mp3 \
+  --optimize-zh \
+  --language zh \
+  --max-speakers 5 \
+  --output meeting_result.json
+```
+
+### Batch processing (half-price)
+
+```bash
+# Submit in batch mode — processed during off-peak hours, 50% discount
+auralwise transcribe https://storage.example.com/archive.mp3 \
+  --batch \
+  --no-wait \
+  --callback-url https://your-server.com/webhook
+```
+
+### Audio event detection only
+
+```bash
+auralwise transcribe ./audio.mp3 \
+  --no-asr \
+  --no-diarize \
+  --events-classes "Cough,Music,Applause" \
+  --json
+```
+
+### Transcription only (no diarization, no events)
+
+```bash
+auralwise transcribe ./podcast.mp3 \
+  --no-diarize \
+  --no-events \
+  --hotwords "AuralWise,PGPU" \
+  --output transcript.json
+```
+
+## Output Format
+
+### Pretty-printed (default)
+
+```
+Audio Duration: 5.3min
+Language: zh (99%)
+Speakers: 2
+
+Transcription
+
+[0:00.5 - 0:02.3] SPEAKER_0: This is the first sentence
+[0:02.5 - 0:04.1] SPEAKER_1: And this is the reply
+
+Audio Events
+
+[0:45.0 - 0:45.9] Cough (87%)
+[1:20.0 - 1:25.0] Music (92%)
+
+Speaker Embeddings
+
+  SPEAKER_0: 25 segments, 192-dim vector
+  SPEAKER_1: 18 segments, 192-dim vector
+```
+
+### JSON (`--json`)
+
+Returns the full API response. See [API documentation](https://auralwise.cn/api-docs) for the complete schema.
+
+## Pricing
+
+| Capability | Standard | Batch (50% off) |
+|-----------|----------|-----------------|
+| Chinese transcription | ¥0.27/hr | ¥0.14/hr |
+| General transcription (with word timestamps) | ¥1.20/hr | ¥0.60/hr |
+| Speaker diarization (labels + embeddings) | +¥0.40/hr | +¥0.20/hr |
+| Audio event detection (521 classes) | +¥0.10/hr | +¥0.05/hr |
+
+**Example: 100 hours of Chinese meetings (full features) = ¥39 in batch mode.**
+
+## API Documentation
+
+Full API reference: https://auralwise.cn/api-docs
+
+## License
+
+MIT

package/README_CN.md

@@ -0,0 +1,270 @@
+# AuralWise CLI
+
+[English](./README.md)
+
+[AuralWise](https://auralwise.cn) 语音智能 API 的命令行工具。
+
+一次调用，同时返回转写、说话人分离、声纹向量、词级时间戳和 521 类声音事件 —— 花接近基础转写的钱，拿到完整可用的结构化结果。
+
+## 核心能力
+
+- **语音转写** — 支持 99 种语言，中文场景使用专用引擎（`optimize_zh`），速度更快、准确率更高
+- **说话人分离** — 自动检测说话人数量，为每段文本标注说话人标签
+- **说话人声纹向量** — 192 维声纹向量，可用于跨录音比对同一说话人
+- **精准时间戳** — 词级（~10ms）或段级（~100ms）精度
+- **声音事件检测** — 521 类 AudioSet 声音事件（掌声、咳嗽、音乐、键盘声等）
+- **语音活动检测** — VAD 语音段识别
+- **批量模式** — 使用闲时 GPU 算力，价格直接五折，24 小时内交付
+
+## 安装
+
+```bash
+npm install -g auralwise_cli
+```
+
+需要 Node.js >= 18。
+
+## 快速上手
+
+```bash
+# 设置 API Key（在 https://auralwise.cn 获取）
+export AURALWISE_API_KEY=asr_xxxxxxxxxxxxxxxxxxxx
+
+# URL 模式转写 — 等待完成并输出结果
+auralwise transcribe https://example.com/meeting.mp3
+
+# 本地文件转写（自动 base64 上传）
+auralwise transcribe ./recording.wav
+
+# 中文精简模式（更快、更便宜）
+auralwise transcribe ./meeting.mp3 --optimize-zh --language zh
+
+# 提交后立即返回，不等待完成
+auralwise transcribe https://example.com/audio.mp3 --no-wait
+
+# JSON 输出并保存到文件
+auralwise transcribe ./audio.mp3 --json --output result.json
+
+# 使用中文界面
+auralwise --locale zh transcribe --help
+```
+
+## 命令列表
+
+### `auralwise transcribe <source>`
+
+提交音频进行处理。`<source>` 可以是 HTTP(S) URL 或本地文件路径。
+
+**输入方式：**
+- **URL 模式** — 传入 `https://...` URL，GPU 节点直接下载
+- **文件模式** — 传入本地文件路径，CLI 读取文件并以 base64 上传
+
+**常用选项：**
+
+| 选项 | 说明 |
+|------|------|
+| `--language <lang>` | ASR 识别语言（`zh`、`en`、`ja` 等），不指定则自动检测 |
+| `--optimize-zh` | 使用中文专用引擎（更快、更便宜，段级时间戳） |
+| `--no-asr` | 禁用语音转写 |
+| `--no-diarize` | 禁用说话人分离 |
+| `--no-events` | 禁用声音事件检测 |
+| `--hotwords <words>` | 热词列表（逗号分隔），提升专有名词识别率 |
+| `--num-speakers <n>` | 指定固定说话人数 |
+| `--max-speakers <n>` | 自动检测时最大说话人数（默认 10） |
+| `--batch` | 批量模式（五折价格，24 小时内完成） |
+| `--no-wait` | 提交后立即返回，不轮询等待 |
+| `--json` | 以 JSON 格式输出 |
+| `--output <file>` | 将结果保存到文件 |
+| `--callback-url <url>` | Webhook 回调 URL，任务完成后通知 |
+
+**高级 ASR 选项：**
+
+| 选项 | 说明 |
+|------|------|
+| `--beam-size <n>` | Beam Search 宽度（默认 5） |
+| `--temperature <n>` | 解码温度（默认 0.0） |
+| `--initial-prompt <text>` | 初始提示文本，引导转写风格 |
+| `--vad-threshold <n>` | VAD 语音检测阈值 0-1（默认 0.35） |
+| `--events-threshold <n>` | 声音事件置信度阈值（默认 0.3） |
+| `--events-classes <list>` | 仅检测指定的事件类别 |
+
+### `auralwise tasks`
+
+查看任务列表，支持按状态过滤和分页。
+
+```bash
+auralwise tasks                          # 列出所有任务
+auralwise tasks --status done            # 仅已完成的任务
+auralwise tasks --page 2 --page-size 50  # 分页
+auralwise tasks --json                   # JSON 输出
+```
+
+### `auralwise task <id>`
+
+查看单个任务的详细信息。
+
+```bash
+auralwise task 550e8400-e29b-41d4-a716-446655440000
+auralwise task 550e8400-e29b-41d4-a716-446655440000 --json
+```
+
+### `auralwise result <id>`
+
+获取已完成任务的完整转写结果。
+
+```bash
+auralwise result <task-id>                       # 格式化输出
+auralwise result <task-id> --json                # JSON 输出
+auralwise result <task-id> --output result.json  # 保存到文件
+```
+
+### `auralwise delete <id>`
+
+删除任务及其关联的音频文件和结果。
+
+```bash
+auralwise delete <task-id>           # 删除前确认
+auralwise delete <task-id> --force   # 跳过确认
+```
+
+### `auralwise events`
+
+浏览 521 类 AudioSet 声音事件。
+
+```bash
+auralwise events                       # 列出全部 521 类
+auralwise events --search 咳嗽         # 按名称搜索
+auralwise events --category Music      # 按类别过滤
+auralwise events --json                # JSON 输出
+```
+
+## 配置
+
+### API Key
+
+通过 `--api-key` 参数或环境变量设置：
+
+```bash
+# 环境变量（推荐）
+export AURALWISE_API_KEY=asr_xxxxxxxxxxxxxxxxxxxx
+
+# 或直接传入
+auralwise --api-key asr_xxxx transcribe ./audio.mp3
+```
+
+### 自定义 API 地址
+
+私有化部署时可修改 API 地址（默认 `https://auralwise.cn/api/v1`）：
+
+```bash
+auralwise --base-url https://your-private-instance.com/api/v1 transcribe ./audio.mp3
+```
+
+### 界面语言
+
+CLI 支持中英文界面切换：
+
+```bash
+auralwise --locale zh --help             # 中文界面
+auralwise --locale en transcribe --help  # 英文界面（默认）
+```
+
+## 使用示例
+
+### 会议录音转写 + 说话人分离
+
+```bash
+auralwise transcribe ./meeting.mp3 \
+  --optimize-zh \
+  --language zh \
+  --max-speakers 5 \
+  --output meeting_result.json
+```
+
+### 批量处理（五折价格）
+
+```bash
+# 批量模式 — 利用闲时算力处理，价格直接五折
+auralwise transcribe https://storage.example.com/archive.mp3 \
+  --batch \
+  --no-wait \
+  --callback-url https://your-server.com/webhook
+```
+
+### 仅声音事件检测
+
+```bash
+auralwise transcribe ./audio.mp3 \
+  --no-asr \
+  --no-diarize \
+  --events-classes "Cough,Music,Applause" \
+  --json
+```
+
+### 仅转写（不需要说话人分离和事件检测）
+
+```bash
+auralwise transcribe ./podcast.mp3 \
+  --no-diarize \
+  --no-events \
+  --hotwords "AuralWise,PGPU" \
+  --output transcript.json
+```
+
+## 输出格式
+
+### 格式化输出（默认）
+
+```
+Audio Duration: 5.3min
+Language: zh (99%)
+Speakers: 2
+
+Transcription
+
+[0:00.5 - 0:02.3] SPEAKER_0: 好的，我们先来看第一个议题
+[0:02.5 - 0:04.1] SPEAKER_1: 没问题，请继续
+
+Audio Events
+
+[0:45.0 - 0:45.9] Cough (87%)
+[1:20.0 - 1:25.0] Music (92%)
+
+Speaker Embeddings
+
+  SPEAKER_0: 25 segments, 192-dim vector
+  SPEAKER_1: 18 segments, 192-dim vector
+```
+
+### JSON 输出（`--json`）
+
+返回完整的 API 响应，详见 [API 文档](https://auralwise.cn/api-docs)。
+
+## 定价
+
+| 能力 | 标准价格 | 批量模式（五折） |
+|------|---------|----------------|
+| 中文转写 | ¥0.27/小时 | ¥0.14/小时 |
+| 通用转写（含词级时间戳） | ¥1.20/小时 | ¥0.60/小时 |
+| 说话人分离（标签 + 声纹向量） | +¥0.40/小时 | +¥0.20/小时 |
+| 声音事件检测（521 类） | +¥0.10/小时 | +¥0.05/小时 |
+
+**示例：100 小时中文会议录音（全功能）= 批量模式仅需 ¥39。**
+
+## 适用场景
+
+- **会议纪要与知识库** — 自动识别每位发言人，生成结构化会议记录
+- **客服录音质检** — 多角色对话分析，配合声音事件检测辅助质检
+- **访谈 / 播客整理** — 批量转写，按说话人切分段落，快速生成字幕
+- **法务 / 合规留档** — 支持私有化部署，数据不出域，方便检索和证据提取
+- **课程 / 教育内容** — 课堂录音批量处理，生成带时间戳的字幕
+- **影视 / 字幕制作** — 词级时间戳直接生成时间轴字幕
+- **历史档案数字化** — 批量模式低成本处理历史录音
+
+## API 文档
+
+完整 API 参考：https://auralwise.cn/api-docs
+
+## 许可证
+
+MIT

package/bin/auralwise.js

@@ -20,7 +20,7 @@ const program = new Command();
 program
   .name('auralwise')
   .description(t('descMain'))
-  .version('1.0.1')
+  .version('1.0.3')
   .option('--api-key <key>', t('optApiKey'))
   .option('--base-url <url>', t('optBaseUrl'), 'https://auralwise.cn/api/v1')
   .option('--locale <locale>', t('optLocale'));

package/lib/i18n.js

@@ -98,14 +98,19 @@ const messages = {
     category: 'Category',
     noEventsFound: 'No matching events found.',
 
+    // Result display - additional
+    vadSegments: 'VAD Segments',
+    diarizeSegments: 'Diarize Segments',
+    langProb: 'Language Probability',
+
     // Command descriptions
-    descMain: 'CLI for AuralWise audio intelligence API',
+    descMain: 'AuralWise Speech Intelligence API CLI\n\n  Transcription, speaker diarization, speaker embeddings,\n  word-level timestamps, and 521-class audio event detection\n  — all in one API call.',
     descTranscribe: 'Submit an audio transcription task (URL or local file)',
     descTasks: 'List tasks',
     descTask: 'Get task details',
     descResult: 'Get task result',
     descDelete: 'Delete a task',
-    descEvents: 'List audio event classes (521 classes)',
+    descEvents: 'List all 521 AudioSet sound event classes',
     argSource: 'Audio URL or local file path',
     argTaskId: 'Task ID',
   },
@@ -208,14 +213,19 @@ const messages = {
     category: '类别',
     noEventsFound: '未找到匹配的事件。',
 
+    // Result display - additional
+    vadSegments: 'VAD 语音段',
+    diarizeSegments: '说话人分离段',
+    langProb: '语言置信度',
+
     // Command descriptions
-    descMain: 'AuralWise 语音智能 API 命令行工具',
+    descMain: 'AuralWise 语音智能 API 命令行工具\n\n  转写、说话人分离、声纹向量、词级时间戳、521 类声音事件检测\n  —— 一次调用，全部返回。',
     descTranscribe: '提交音频转写任务（URL 或本地文件）',
     descTasks: '列出任务',
     descTask: '查看任务详情',
     descResult: '获取任务结果',
     descDelete: '删除任务',
-    descEvents: '列出声音事件类别（521 类）',
+    descEvents: '列出全部 521 类 AudioSet 声音事件',
     argSource: '音频 URL 或本地文件路径',
     argTaskId: '任务 ID',
   },

package/lib/utils.js

@@ -85,6 +85,32 @@ export function printResult(result) {
       console.log(`  ${chalk.cyan(spk.speaker_id)}: ${spk.segment_count} ${t('segments')}, ${spk.embedding.length}${t('dimVector')}`);
     }
   }
+
+  if (result.vad_segments && result.vad_segments.length > 0) {
+    console.log();
+    console.log(chalk.bold.underline(`${t('vadSegments')} (${result.vad_segments.length})`));
+    console.log();
+    for (const seg of result.vad_segments.slice(0, 20)) {
+      const dur = (seg.end - seg.start).toFixed(1);
+      console.log(`  [${formatTime(seg.start)} - ${formatTime(seg.end)}] ${chalk.dim(`${dur}s`)}`);
+    }
+    if (result.vad_segments.length > 20) {
+      console.log(chalk.dim(`  ... +${result.vad_segments.length - 20} more`));
+    }
+  }
+
+  if (result.diarize_segments && result.diarize_segments.length > 0) {
+    console.log();
+    console.log(chalk.bold.underline(`${t('diarizeSegments')} (${result.diarize_segments.length})`));
+    console.log();
+    for (const seg of result.diarize_segments.slice(0, 20)) {
+      const dur = (seg.end - seg.start).toFixed(1);
+      console.log(`  [${formatTime(seg.start)} - ${formatTime(seg.end)}] ${chalk.cyan(seg.speaker)} ${chalk.dim(`${dur}s`)}`);
+    }
+    if (result.diarize_segments.length > 20) {
+      console.log(chalk.dim(`  ... +${result.diarize_segments.length - 20} more`));
+    }
+  }
 }
 
 export function printTaskDetail(task) {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "auralwise_cli",
-  "version": "1.0.1",
+  "version": "1.0.3",
   "description": "CLI for AuralWise audio intelligence API - transcription, speaker diarization, audio event detection",
   "type": "module",
   "bin": {
@@ -8,7 +8,8 @@
   },
   "files": [
     "bin/",
-    "lib/"
+    "lib/",
+    "README_CN.md"
   ],
   "scripts": {
     "test": "vitest run",