auralwise_cli 1.0.0 → 1.0.2

package/README.md

@@ -0,0 +1,255 @@
+# AuralWise CLI
+
+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/bin/auralwise.js

@@ -9,21 +9,21 @@ import { registerResult } from '../lib/commands/result.js';
 import { registerDelete } from '../lib/commands/delete.js';
 import { registerEvents } from '../lib/commands/events.js';
 
-const program = new Command();
-
 // Parse --locale early before command registration so descriptions use correct language
 const localeIdx = process.argv.indexOf('--locale');
 if (localeIdx !== -1 && process.argv[localeIdx + 1]) {
   setLocale(process.argv[localeIdx + 1]);
 }
 
+const program = new Command();
+
 program
   .name('auralwise')
   .description(t('descMain'))
-  .version('1.0.0')
-  .option('--api-key <key>', 'API key (or set AURALWISE_API_KEY env)')
-  .option('--base-url <url>', 'API base URL', 'https://auralwise.cn/api/v1')
-  .option('--locale <locale>', 'UI language: en or zh (default: en)');
+  .version('1.0.2')
+  .option('--api-key <key>', t('optApiKey'))
+  .option('--base-url <url>', t('optBaseUrl'), 'https://auralwise.cn/api/v1')
+  .option('--locale <locale>', t('optLocale'));
 
 registerTranscribe(program);
 registerTasks(program);

package/lib/commands/delete.js

@@ -7,7 +7,7 @@ export function registerDelete(program) {
     .command('delete')
     .description(t('descDelete'))
     .argument('<id>', t('argTaskId'))
-    .option('--force', 'Skip confirmation')
+    .option('--force', t('optForce'))
     .action(async (id, opts) => {
       try {
         if (!opts.force) {
@@ -27,7 +27,7 @@ export function registerDelete(program) {
         await client.deleteTask(id);
         console.log(chalk.green(t('taskDeleted', { id: id.substring(0, 8) })));
       } catch (err) {
-        console.error(chalk.red(`Error: ${err.message}`));
+        console.error(chalk.red(`${t('error')}: ${err.message}`));
         process.exit(1);
       }
     });

package/lib/commands/events.js

@@ -6,9 +6,9 @@ export function registerEvents(program) {
   program
     .command('events')
     .description(t('descEvents'))
-    .option('--category <cat>', 'Filter by category')
-    .option('--search <keyword>', 'Search event name')
-    .option('--json', 'Output as JSON')
+    .option('--category <cat>', t('optCategory'))
+    .option('--search <keyword>', t('optSearch'))
+    .option('--json', t('optJson'))
     .action(async (opts) => {
       try {
         const client = createClient(program);
@@ -43,7 +43,7 @@ export function registerEvents(program) {
         const isZh = getLocale() === 'zh';
         console.log(chalk.bold(`${t('totalClasses')}: ${classes.length}`));
         console.log();
-        console.log(chalk.bold('Index  Name                                    Category'));
+        console.log(chalk.bold(`${t('tableHeaderIndex').padStart(5)}  ${t('tableHeaderName').padEnd(40)}  ${t('category')}`));
         console.log('─'.repeat(80));
         for (const c of classes) {
           const name = isZh ? (c.zh_name || c.display_name) : c.display_name;
@@ -51,7 +51,7 @@ export function registerEvents(program) {
           console.log(`${String(c.index).padStart(5)}  ${name.padEnd(40)}  ${cat}`);
         }
       } catch (err) {
-        console.error(chalk.red(`Error: ${err.message}`));
+        console.error(chalk.red(`${t('error')}: ${err.message}`));
         process.exit(1);
       }
     });

package/lib/commands/result.js

@@ -8,8 +8,8 @@ export function registerResult(program) {
     .command('result')
     .description(t('descResult'))
     .argument('<id>', t('argTaskId'))
-    .option('--json', 'Output as JSON')
-    .option('--output <file>', 'Save result to file')
+    .option('--json', t('optJson'))
+    .option('--output <file>', t('optOutput'))
     .action(async (id, opts) => {
       try {
         const client = createClient(program);
@@ -24,7 +24,7 @@ export function registerResult(program) {
           printResult(result);
         }
       } catch (err) {
-        console.error(chalk.red(`Error: ${err.message}`));
+        console.error(chalk.red(`${t('error')}: ${err.message}`));
         process.exit(1);
       }
     });

package/lib/commands/task.js

@@ -7,7 +7,7 @@ export function registerTask(program) {
     .command('task')
     .description(t('descTask'))
     .argument('<id>', t('argTaskId'))
-    .option('--json', 'Output as JSON')
+    .option('--json', t('optJson'))
     .action(async (id, opts) => {
       try {
         const client = createClient(program);
@@ -19,7 +19,7 @@ export function registerTask(program) {
           printTaskDetail(task);
         }
       } catch (err) {
-        console.error(chalk.red(`Error: ${err.message}`));
+        console.error(chalk.red(`${t('error')}: ${err.message}`));
         process.exit(1);
       }
     });

package/lib/commands/tasks.js

@@ -6,10 +6,10 @@ export function registerTasks(program) {
   program
     .command('tasks')
     .description(t('descTasks'))
-    .option('--status <status>', 'Filter by status (pending/processing/done/failed/abandoned)')
-    .option('--page <n>', 'Page number', parseInt, 1)
-    .option('--page-size <n>', 'Items per page', parseInt, 20)
-    .option('--json', 'Output as JSON')
+    .option('--status <status>', t('optStatus'))
+    .option('--page <n>', t('optPage'), parseInt, 1)
+    .option('--page-size <n>', t('optPageSize'), parseInt, 20)
+    .option('--json', t('optJson'))
     .action(async (opts) => {
       try {
         const client = createClient(program);
@@ -30,7 +30,7 @@ export function registerTasks(program) {
           return;
         }
 
-        console.log(chalk.bold('ID        Status               Filename                                  Created'));
+        console.log(chalk.bold(`${t('tableHeaderId').padEnd(10)}${t('tableHeaderStatus').padEnd(20)}${t('tableHeaderFilename').padEnd(42)}${t('tableHeaderCreated')}`));
         console.log('─'.repeat(100));
         for (const task of tasks) {
           console.log(formatTaskRow(task));
@@ -38,7 +38,7 @@ export function registerTasks(program) {
         console.log('─'.repeat(100));
         console.log(`${t('total')}: ${data.total || tasks.length}  ${t('page')}: ${data.page || 1}/${Math.ceil((data.total || tasks.length) / (data.page_size || 20))}`);
       } catch (err) {
-        console.error(chalk.red(`Error: ${err.message}`));
+        console.error(chalk.red(`${t('error')}: ${err.message}`));
         process.exit(1);
       }
     });

package/lib/commands/transcribe.js

@@ -10,32 +10,32 @@ export function registerTranscribe(program) {
     .command('transcribe')
     .description(t('descTranscribe'))
     .argument('<source>', t('argSource'))
-    .option('--base64', 'Force base64 mode for local file upload')
-    .option('--language <lang>', 'ASR language (zh/en/ja/... or null for auto)')
-    .option('--no-asr', 'Disable ASR')
-    .option('--no-diarize', 'Disable speaker diarization')
-    .option('--no-events', 'Disable audio event detection')
-    .option('--optimize-zh', 'Enable Chinese optimization mode')
-    .option('--beam-size <n>', 'Beam search width', parseInt)
-    .option('--temperature <n>', 'Decoding temperature', parseFloat)
-    .option('--hotwords <words>', 'Hotwords (comma-separated)')
-    .option('--initial-prompt <text>', 'Initial prompt text')
-    .option('--vad-threshold <n>', 'VAD threshold (0-1)', parseFloat)
-    .option('--vad-min-speech <ms>', 'Min speech duration in ms', parseInt)
-    .option('--vad-min-silence <ms>', 'Min silence duration in ms', parseInt)
-    .option('--no-speech-threshold <n>', 'No-speech probability threshold', parseFloat)
-    .option('--num-speakers <n>', 'Fixed number of speakers', parseInt)
-    .option('--min-speakers <n>', 'Minimum speakers for auto-detection', parseInt)
-    .option('--max-speakers <n>', 'Maximum speakers for auto-detection', parseInt)
-    .option('--events-threshold <n>', 'Audio event confidence threshold', parseFloat)
-    .option('--events-classes <classes>', 'Specific event classes (comma-separated)')
-    .option('--batch', 'Enable batch mode (lower priority)')
-    .option('--callback-url <url>', 'Webhook callback URL')
-    .option('--callback-secret <secret>', 'Webhook HMAC secret')
-    .option('--no-wait', 'Submit and return immediately without polling')
-    .option('--poll-interval <seconds>', 'Polling interval in seconds', parseFloat, 5)
-    .option('--json', 'Output as JSON')
-    .option('--output <file>', 'Save result to file')
+    .option('--base64', t('optBase64'))
+    .option('--language <lang>', t('optLanguage'))
+    .option('--no-asr', t('optNoAsr'))
+    .option('--no-diarize', t('optNoDiarize'))
+    .option('--no-events', t('optNoEvents'))
+    .option('--optimize-zh', t('optOptimizeZh'))
+    .option('--beam-size <n>', t('optBeamSize'), parseInt)
+    .option('--temperature <n>', t('optTemperature'), parseFloat)
+    .option('--hotwords <words>', t('optHotwords'))
+    .option('--initial-prompt <text>', t('optInitialPrompt'))
+    .option('--vad-threshold <n>', t('optVadThreshold'), parseFloat)
+    .option('--vad-min-speech <ms>', t('optVadMinSpeech'), parseInt)
+    .option('--vad-min-silence <ms>', t('optVadMinSilence'), parseInt)
+    .option('--no-speech-threshold <n>', t('optNoSpeechThreshold'), parseFloat)
+    .option('--num-speakers <n>', t('optNumSpeakers'), parseInt)
+    .option('--min-speakers <n>', t('optMinSpeakers'), parseInt)
+    .option('--max-speakers <n>', t('optMaxSpeakers'), parseInt)
+    .option('--events-threshold <n>', t('optEventsThreshold'), parseFloat)
+    .option('--events-classes <classes>', t('optEventsClasses'))
+    .option('--batch', t('optBatch'))
+    .option('--callback-url <url>', t('optCallbackUrl'))
+    .option('--callback-secret <secret>', t('optCallbackSecret'))
+    .option('--no-wait', t('optNoWait'))
+    .option('--poll-interval <seconds>', t('optPollInterval'), parseFloat, 5)
+    .option('--json', t('optJson'))
+    .option('--output <file>', t('optOutput'))
     .action(async (source, opts) => {
       try {
         const client = createClient(program);
@@ -117,7 +117,7 @@ export function registerTranscribe(program) {
           process.exit(1);
         }
       } catch (err) {
-        console.error(chalk.red(`Error: ${err.message}`));
+        console.error(chalk.red(`${t('error')}: ${err.message}`));
         process.exit(1);
       }
     });

package/lib/i18n.js

@@ -2,13 +2,63 @@ const messages = {
   en: {
     // General
     apiKeyRequired: 'Error: API key required. Use --api-key or set AURALWISE_API_KEY environment variable.',
-    // Transcribe
+    // Global options
+    optApiKey: 'API key (or set AURALWISE_API_KEY env)',
+    optBaseUrl: 'API base URL',
+    optLocale: 'UI language: en or zh (default: en)',
+
+    // Transcribe command
     submittingTask: 'Submitting task...',
     taskCreated: 'Task created',
     waitingTask: 'Waiting for task to complete...',
     taskCompleted: 'Task completed!',
     taskFailed: 'Task {status}: {error}',
     resultSaved: 'Result saved to {file}',
+    optBase64: 'Force base64 mode for local file upload',
+    optLanguage: 'ASR language (zh/en/ja/... or null for auto)',
+    optNoAsr: 'Disable ASR',
+    optNoDiarize: 'Disable speaker diarization',
+    optNoEvents: 'Disable audio event detection',
+    optOptimizeZh: 'Enable Chinese optimization mode',
+    optBeamSize: 'Beam search width',
+    optTemperature: 'Decoding temperature',
+    optHotwords: 'Hotwords (comma-separated)',
+    optInitialPrompt: 'Initial prompt text',
+    optVadThreshold: 'VAD threshold (0-1)',
+    optVadMinSpeech: 'Min speech duration in ms',
+    optVadMinSilence: 'Min silence duration in ms',
+    optNoSpeechThreshold: 'No-speech probability threshold',
+    optNumSpeakers: 'Fixed number of speakers',
+    optMinSpeakers: 'Minimum speakers for auto-detection',
+    optMaxSpeakers: 'Maximum speakers for auto-detection',
+    optEventsThreshold: 'Audio event confidence threshold',
+    optEventsClasses: 'Specific event classes (comma-separated)',
+    optBatch: 'Enable batch mode (lower priority)',
+    optCallbackUrl: 'Webhook callback URL',
+    optCallbackSecret: 'Webhook HMAC secret',
+    optNoWait: 'Submit and return immediately without polling',
+    optPollInterval: 'Polling interval in seconds',
+    optJson: 'Output as JSON',
+    optOutput: 'Save result to file',
+
+    // Tasks command
+    optStatus: 'Filter by status (pending/processing/done/failed/abandoned)',
+    optPage: 'Page number',
+    optPageSize: 'Items per page',
+    tableHeaderId: 'ID',
+    tableHeaderStatus: 'Status',
+    tableHeaderFilename: 'Filename',
+    tableHeaderCreated: 'Created',
+
+    // Delete command
+    optForce: 'Skip confirmation',
+
+    // Events command
+    optCategory: 'Filter by category',
+    optSearch: 'Search event name',
+    tableHeaderIndex: 'Index',
+    tableHeaderName: 'Name',
+
     // Result display
     audioDuration: 'Audio Duration',
     language: 'Language',
@@ -18,6 +68,7 @@ const messages = {
     speakerEmbeddings: 'Speaker Embeddings',
     segments: 'segments',
     dimVector: '-dim vector',
+
     // Task detail
     taskId: 'Task ID',
     status: 'Status',
@@ -31,37 +82,99 @@ const messages = {
     progress: 'Progress',
     error: 'Error',
     options: 'Options',
+
     // Tasks list
     noTasks: 'No tasks found.',
     total: 'Total',
     page: 'Page',
+
     // Delete
     taskDeleted: 'Task {id} deleted.',
     confirmDelete: 'Are you sure you want to delete task {id}?',
     deleteCancelled: 'Delete cancelled.',
+
     // Events
     totalClasses: 'Total event classes',
     category: 'Category',
     noEventsFound: 'No matching events found.',
-    // Descriptions
-    descMain: 'CLI for AuralWise audio intelligence API',
+
+    // Result display - additional
+    vadSegments: 'VAD Segments',
+    diarizeSegments: 'Diarize Segments',
+    langProb: 'Language Probability',
+
+    // Command descriptions
+    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',
   },
   zh: {
+    // General
     apiKeyRequired: '错误：需要 API Key。请使用 --api-key 参数或设置 AURALWISE_API_KEY 环境变量。',
+    // Global options
+    optApiKey: 'API 密钥（或设置 AURALWISE_API_KEY 环境变量）',
+    optBaseUrl: 'API 基础 URL',
+    optLocale: '界面语言：en 或 zh（默认 en）',
+
+    // Transcribe command
     submittingTask: '提交任务中...',
     taskCreated: '任务已创建',
     waitingTask: '等待任务完成...',
     taskCompleted: '任务完成！',
     taskFailed: '任务{status}：{error}',
     resultSaved: '结果已保存到 {file}',
+    optBase64: '强制使用 Base64 模式上传本地文件',
+    optLanguage: 'ASR 识别语言（zh/en/ja/... 或留空自动检测）',
+    optNoAsr: '禁用语音转写',
+    optNoDiarize: '禁用说话人分离',
+    optNoEvents: '禁用声音事件检测',
+    optOptimizeZh: '启用中文精简模式',
+    optBeamSize: 'Beam Search 宽度',
+    optTemperature: '解码温度',
+    optHotwords: '热词（逗号分隔）',
+    optInitialPrompt: '初始提示文本',
+    optVadThreshold: 'VAD 语音检测阈值（0-1）',
+    optVadMinSpeech: '最短语音段时长（毫秒）',
+    optVadMinSilence: '最短静音间隔（毫秒）',
+    optNoSpeechThreshold: '无语音概率阈值',
+    optNumSpeakers: '固定说话人数',
+    optMinSpeakers: '自动检测最少说话人数',
+    optMaxSpeakers: '自动检测最多说话人数',
+    optEventsThreshold: '声音事件置信度阈值',
+    optEventsClasses: '指定事件类别（逗号分隔）',
+    optBatch: '启用批量模式（低优先级）',
+    optCallbackUrl: 'Webhook 回调 URL',
+    optCallbackSecret: 'Webhook HMAC 签名密钥',
+    optNoWait: '提交后立即返回，不等待完成',
+    optPollInterval: '轮询间隔（秒）',
+    optJson: '以 JSON 格式输出',
+    optOutput: '将结果保存到文件',
+
+    // Tasks command
+    optStatus: '按状态过滤（pending/processing/done/failed/abandoned）',
+    optPage: '页码',
+    optPageSize: '每页数量',
+    tableHeaderId: 'ID',
+    tableHeaderStatus: '状态',
+    tableHeaderFilename: '文件名',
+    tableHeaderCreated: '创建时间',
+
+    // Delete command
+    optForce: '跳过确认',
+
+    // Events command
+    optCategory: '按类别过滤',
+    optSearch: '搜索事件名称',
+    tableHeaderIndex: '序号',
+    tableHeaderName: '名称',
+
+    // Result display
     audioDuration: '音频时长',
     language: '语言',
     speakers: '说话人数',
@@ -70,6 +183,8 @@ const messages = {
     speakerEmbeddings: '声纹向量',
     segments: '段',
     dimVector: '维向量',
+
+    // Task detail
     taskId: '任务 ID',
     status: '状态',
     source: '来源',
@@ -82,22 +197,35 @@ const messages = {
     progress: '进度',
     error: '错误',
     options: '选项',
+
+    // Tasks list
     noTasks: '没有找到任务。',
     total: '总计',
     page: '页',
+
+    // Delete
     taskDeleted: '任务 {id} 已删除。',
     confirmDelete: '确定要删除任务 {id} 吗？',
     deleteCancelled: '已取消删除。',
+
+    // Events
     totalClasses: '事件类别总数',
     category: '类别',
     noEventsFound: '未找到匹配的事件。',
-    descMain: 'AuralWise 语音智能 API 命令行工具',
+
+    // 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\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": "1.0.0",
+  "version": "1.0.2",
   "description": "CLI for AuralWise audio intelligence API - transcription, speaker diarization, audio event detection",
   "type": "module",
   "bin": {