[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77NYDS3SWEM4BWHXDC3MYR1":3,"skill-same:01M77NYDS3SWEM4BWHXDC3MYR1":56},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":13,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M77NYDS3SWEM4BWHXDC3MYR1","TTS",null,"Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.","nordeim\u002Fstory-into-video","nordeim","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F194583642?v=4","01M75CZEV8C3V4DDQNPQ1EA7QJ","01M77NXQ9G1G1YWJMQTCEFSG23",0,"MIT","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002FTTS\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002FTTS\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: TTS\ndescription: Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.\nlicense: MIT\n---\n\n# TTS (Text to Speech) Skill\n\nThis skill guides the implementation of text-to-speech (TTS) functionality using the z-ai-web-dev-sdk package, enabling conversion of text into natural-sounding speech audio.\n\n## Skills Path\n\n**Skill Location**: `{project_path}\u002Fskills\u002FTTS`\n\nThis skill is located at the above path in your project.\n\n**Reference Scripts**: Example test scripts are available in the `{Skill Location}\u002Fscripts\u002F` directory for quick testing and reference. See `{Skill Location}\u002Fscripts\u002Ftts.ts` for a working example.\n\n## Overview\n\nText-to-Speech allows you to build applications that generate spoken audio from text input, supporting various voices, speeds, and output formats for diverse use cases.\n\n**IMPORTANT**: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.\n\n## API Limitations and Constraints\n\nBefore implementing TTS functionality, be aware of these important limitations:\n\n### Input Text Constraints\n- **Maximum length**: 1024 characters per request\n- Text exceeding this limit must be split into smaller chunks\n\n### Audio Parameters\n- **Speed range**: 0.5 to 2.0\n  - 0.5 = half speed (slower)\n  - 1.0 = normal speed (default)\n  - 2.0 = double speed (faster)\n- **Volume range**: Greater than 0, up to 10\n  - Default: 1.0\n  - Values must be greater than 0 (exclusive) and up to 10 (inclusive)\n\n### Format and Streaming\n- **Streaming limitation**: When `stream: true` is enabled, only `pcm` format is supported\n- **Non-streaming**: Supports `wav`, `pcm`, and `mp3` formats\n- **Sample rate**: 24000 Hz (recommended)\n\n### Best Practice for Long Text\n```javascript\nfunction splitTextIntoChunks(text, maxLength = 1000) {\n  const chunks = [];\n  const sentences = text.match(\u002F[^.!?]+[.!?]+\u002Fg) || [text];\n  \n  let currentChunk = '';\n  for (const sentence of sentences) {\n    if ((currentChunk + sentence).length \u003C= maxLength) {\n      currentChunk += sentence;\n    } else {\n      if (currentChunk) chunks.push(currentChunk.trim());\n      currentChunk = sentence;\n    }\n  }\n  if (currentChunk) chunks.push(currentChunk.trim());\n  \n  return chunks;\n}\n```\n\n## Prerequisites\n\nThe z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below.\n\n## CLI Usage (For Simple Tasks)\n\nFor simple text-to-speech conversions, you can use the z-ai CLI instead of writing code. This is ideal for quick audio generation, testing voices, or simple automation.\n\n### Basic TTS\n\n```bash\n# Convert text to speech (default WAV format)\nz-ai tts --input \"Hello, world\" --output .\u002Fhello.wav\n\n# Using short options\nz-ai tts -i \"Hello, world\" -o .\u002Fhello.wav\n```\n\n### Different Voices and Speed\n\n```bash\n# Use specific voice\nz-ai tts -i \"Welcome to our service\" -o .\u002Fwelcome.wav --voice tongtong\n\n# Adjust speech speed (0.5-2.0)\nz-ai tts -i \"This is faster speech\" -o .\u002Ffast.wav --speed 1.5\n\n# Slower speech\nz-ai tts -i \"This is slower speech\" -o .\u002Fslow.wav --speed 0.8\n```\n\n### Different Output Formats\n\n```bash\n# MP3 format\nz-ai tts -i \"Hello World\" -o .\u002Fhello.mp3 --format mp3\n\n# WAV format (default)\nz-ai tts -i \"Hello World\" -o .\u002Fhello.wav --format wav\n\n# PCM format\nz-ai tts -i \"Hello World\" -o .\u002Fhello.pcm --format pcm\n```\n\n### Streaming Output\n\n```bash\n# Stream audio generation\nz-ai tts -i \"This is a longer text that will be streamed\" -o .\u002Fstream.wav --stream\n```\n\n### CLI Parameters\n\n- `--input, -i \u003Ctext>`: **Required** - Text to convert to speech (max 1024 characters)\n- `--output, -o \u003Cpath>`: **Required** - Output audio file path\n- `--voice, -v \u003Cvoice>`: Optional - Voice type (default: tongtong)\n- `--speed, -s \u003Cnumber>`: Optional - Speech speed, 0.5-2.0 (default: 1.0)\n- `--format, -f \u003Cformat>`: Optional - Output format: wav, mp3, pcm (default: wav)\n- `--stream`: Optional - Enable streaming output (only supports pcm format)\n\n### When to Use CLI vs SDK\n\n**Use CLI for:**\n- Quick text-to-speech conversions\n- Testing different voices and speeds\n- Simple batch audio generation\n- Command-line automation scripts\n\n**Use SDK for:**\n- Dynamic audio generation in applications\n- Integration with web services\n- Custom audio processing pipelines\n- Production applications with complex requirements\n\n## Basic TTS Implementation\n\n### Simple Text to Speech\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function textToSpeech(text, outputPath) {\n  const zai = await ZAI.create();\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: 'tongtong',\n    speed: 1.0,\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  console.log(`Audio saved to ${outputPath}`);\n  return outputPath;\n}\n\n\u002F\u002F Usage\nawait textToSpeech('Hello, world!', '.\u002Foutput.wav');\n```\n\n### Multiple Voice Options\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function generateWithVoice(text, voice, outputPath) {\n  const zai = await ZAI.create();\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: voice, \u002F\u002F Available voices: tongtong, chuichui, xiaochen, jam, kazi, douji, luodo\n    speed: 1.0,\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  return outputPath;\n}\n\n\u002F\u002F Usage\nawait generateWithVoice('Welcome to our service', 'tongtong', '.\u002Fwelcome.wav');\n```\n\n### Adjustable Speed\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function generateWithSpeed(text, speed, outputPath) {\n  const zai = await ZAI.create();\n\n  \u002F\u002F Speed range: 0.5 to 2.0 (API constraint)\n  \u002F\u002F 0.5 = half speed (slower)\n  \u002F\u002F 1.0 = normal speed (default)\n  \u002F\u002F 2.0 = double speed (faster)\n  \u002F\u002F Values outside this range will cause API errors\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: 'tongtong',\n    speed: speed,\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  return outputPath;\n}\n\n\u002F\u002F Usage - slower narration\nawait generateWithSpeed('This is an important announcement', 0.8, '.\u002Fslow.wav');\n\n\u002F\u002F Usage - faster narration\nawait generateWithSpeed('Quick update', 1.3, '.\u002Ffast.wav');\n```\n\n### Adjustable Volume\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function generateWithVolume(text, volume, outputPath) {\n  const zai = await ZAI.create();\n\n  \u002F\u002F Volume range: greater than 0, up to 10 (API constraint)\n  \u002F\u002F Values must be > 0 (exclusive) and \u003C= 10 (inclusive)\n  \u002F\u002F Default: 1.0 (normal volume)\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: 'tongtong',\n    speed: 1.0,\n    volume: volume, \u002F\u002F Optional parameter\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  return outputPath;\n}\n\n\u002F\u002F Usage - louder audio\nawait generateWithVolume('This is an announcement', 5.0, '.\u002Floud.wav');\n\n\u002F\u002F Usage - quieter audio\nawait generateWithVolume('Whispered message', 0.5, '.\u002Fquiet.wav');\n```\n\n## Advanced Use Cases\n\n### Batch Processing\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\nimport path from 'path';\n\nasync function batchTextToSpeech(textArray, outputDir) {\n  const zai = await ZAI.create();\n  const results = [];\n\n  \u002F\u002F Ensure output directory exists\n  if (!fs.existsSync(outputDir)) {\n    fs.mkdirSync(outputDir, { recursive: true });\n  }\n\n  for (let i = 0; i \u003C textArray.length; i++) {\n    try {\n      const text = textArray[i];\n      const outputPath = path.join(outputDir, `audio_${i + 1}.wav`);\n\n      const response = await zai.audio.tts.create({\n        input: text,\n        voice: 'tongtong',\n        speed: 1.0,\n        response_format: 'wav',\n        stream: false\n      });\n\n      \u002F\u002F Get array buffer from Response object\n      const arrayBuffer = await response.arrayBuffer();\n      const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n      fs.writeFileSync(outputPath, buffer);\n      results.push({\n        success: true,\n        text,\n        path: outputPath\n      });\n    } catch (error) {\n      results.push({\n        success: false,\n        text: textArray[i],\n        error: error.message\n      });\n    }\n  }\n\n  return results;\n}\n\n\u002F\u002F Usage\nconst texts = [\n  'Welcome to chapter one',\n  'Welcome to chapter two',\n  'Welcome to chapter three'\n];\n\nconst results = await batchTextToSpeech(texts, '.\u002Faudio-output');\nconsole.log('Generated:', results.length, 'audio files');\n```\n\n### Dynamic Content Generation\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nclass TTSGenerator {\n  constructor() {\n    this.zai = null;\n  }\n\n  async initialize() {\n    this.zai = await ZAI.create();\n  }\n\n  async generateAudio(text, options = {}) {\n    const {\n      voice = 'tongtong',\n      speed = 1.0,\n      format = 'wav'\n    } = options;\n\n    const response = await this.zai.audio.tts.create({\n      input: text,\n      voice: voice,\n      speed: speed,\n      response_format: format,\n      stream: false\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    return Buffer.from(new Uint8Array(arrayBuffer));\n  }\n\n  async saveAudio(text, outputPath, options = {}) {\n    const buffer = await this.generateAudio(text, options);\n    if (buffer) {\n      fs.writeFileSync(outputPath, buffer);\n      return outputPath;\n    }\n    return null;\n  }\n}\n\n\u002F\u002F Usage\nconst generator = new TTSGenerator();\nawait generator.initialize();\n\nawait generator.saveAudio(\n  'Hello, this is a test',\n  '.\u002Foutput.wav',\n  { speed: 1.2 }\n);\n```\n\n### Next.js API Route Example\n\n```javascript\nimport { NextRequest, NextResponse } from 'next\u002Fserver';\n\nexport async function POST(req: NextRequest) {\n  try {\n    const { text, voice = 'tongtong', speed = 1.0 } = await req.json();\n\n    \u002F\u002F Import ZAI SDK\n    const ZAI = (await import('z-ai-web-dev-sdk')).default;\n\n    \u002F\u002F Create SDK instance\n    const zai = await ZAI.create();\n\n    \u002F\u002F Generate TTS audio\n    const response = await zai.audio.tts.create({\n      input: text.trim(),\n      voice: voice,\n      speed: speed,\n      response_format: 'wav',\n      stream: false,\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n    \u002F\u002F Return audio as response\n    return new NextResponse(buffer, {\n      status: 200,\n      headers: {\n        'Content-Type': 'audio\u002Fwav',\n        'Content-Length': buffer.length.toString(),\n        'Cache-Control': 'no-cache',\n      },\n    });\n  } catch (error) {\n    console.error('TTS API Error:', error);\n\n    return NextResponse.json(\n      {\n        error: error instanceof Error ? error.message : '生成语音失败，请稍后重试',\n      },\n      { status: 500 }\n    );\n  }\n}\n```\n\n## Best Practices\n\n### 1. Text Preparation\n```javascript\nfunction prepareTextForTTS(text) {\n  \u002F\u002F Remove excessive whitespace\n  text = text.replace(\u002F\\s+\u002Fg, ' ').trim();\n\n  \u002F\u002F Expand common abbreviations for better pronunciation\n  const abbreviations = {\n    'Dr.': 'Doctor',\n    'Mr.': 'Mister',\n    'Mrs.': 'Misses',\n    'etc.': 'et cetera'\n  };\n\n  for (const [abbr, full] of Object.entries(abbreviations)) {\n    text = text.replace(new RegExp(abbr, 'g'), full);\n  }\n\n  return text;\n}\n```\n\n### 2. Error Handling\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function safeTTS(text, outputPath) {\n  try {\n    \u002F\u002F Validate input\n    if (!text || text.trim().length === 0) {\n      throw new Error('Text input cannot be empty');\n    }\n\n    if (text.length > 1024) {\n      throw new Error('Text input exceeds maximum length of 1024 characters');\n    }\n\n    const zai = await ZAI.create();\n\n    const response = await zai.audio.tts.create({\n      input: text,\n      voice: 'tongtong',\n      speed: 1.0,\n      response_format: 'wav',\n      stream: false\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n    fs.writeFileSync(outputPath, buffer);\n\n    return {\n      success: true,\n      path: outputPath,\n      size: buffer.length\n    };\n  } catch (error) {\n    console.error('TTS Error:', error);\n    return {\n      success: false,\n      error: error.message\n    };\n  }\n}\n```\n\n### 3. SDK Instance Reuse\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\n\n\u002F\u002F Create a singleton instance\nlet zaiInstance = null;\n\nasync function getZAIInstance() {\n  if (!zaiInstance) {\n    zaiInstance = await ZAI.create();\n  }\n  return zaiInstance;\n}\n\n\u002F\u002F Usage\nconst zai = await getZAIInstance();\nconst response = await zai.audio.tts.create({ ... });\n```\n\n## Common Use Cases\n\n1. **Audiobooks & Podcasts**: Convert written content to audio format\n2. **E-learning**: Create narration for educational content\n3. **Accessibility**: Provide audio versions of text content\n4. **Voice Assistants**: Generate dynamic responses\n5. **Announcements**: Create automated audio notifications\n6. **IVR Systems**: Generate phone system prompts\n7. **Content Localization**: Create audio in different languages\n\n## Integration Examples\n\n### Express.js API Endpoint\n\n```javascript\nimport express from 'express';\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\nimport path from 'path';\n\nconst app = express();\napp.use(express.json());\n\nlet zaiInstance;\nconst outputDir = '.\u002Faudio-output';\n\nasync function initZAI() {\n  zaiInstance = await ZAI.create();\n  if (!fs.existsSync(outputDir)) {\n    fs.mkdirSync(outputDir, { recursive: true });\n  }\n}\n\napp.post('\u002Fapi\u002Ftts', async (req, res) => {\n  try {\n    const { text, voice = 'tongtong', speed = 1.0 } = req.body;\n\n    if (!text) {\n      return res.status(400).json({ error: 'Text is required' });\n    }\n\n    const filename = `tts_${Date.now()}.wav`;\n    const outputPath = path.join(outputDir, filename);\n\n    const response = await zaiInstance.audio.tts.create({\n      input: text,\n      voice: voice,\n      speed: speed,\n      response_format: 'wav',\n      stream: false\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n    fs.writeFileSync(outputPath, buffer);\n\n    res.json({\n      success: true,\n      audioUrl: `\u002Faudio\u002F${filename}`,\n      size: buffer.length\n    });\n  } catch (error) {\n    res.status(500).json({ error: error.message });\n  }\n});\n\napp.use('\u002Faudio', express.static('audio-output'));\n\ninitZAI().then(() => {\n  app.listen(3000, () => {\n    console.log('TTS API running on port 3000');\n  });\n});\n```\n\n## Troubleshooting\n\n**Issue**: \"Input text exceeds maximum length\"\n- **Solution**: Text input is limited to 1024 characters. Split longer text into chunks using the `splitTextIntoChunks` function shown in the API Limitations section\n\n**Issue**: \"Invalid speed parameter\" or unexpected speed behavior\n- **Solution**: Speed must be between 0.5 and 2.0. Check your speed value is within this range\n\n**Issue**: \"Invalid volume parameter\"\n- **Solution**: Volume must be greater than 0 and up to 10. Ensure volume value is in range (0, 10]\n\n**Issue**: \"Stream format not supported\" with WAV\u002FMP3\n- **Solution**: Streaming mode only supports PCM format. Either use `response_format: 'pcm'` with streaming, or disable streaming (`stream: false`) for WAV\u002FMP3 output\n\n**Issue**: \"SDK must be used in backend\"\n- **Solution**: Ensure z-ai-web-dev-sdk is only imported in server-side code\n\n**Issue**: \"TypeError: response.audio is undefined\"\n- **Solution**: The SDK returns a standard Response object, use `await response.arrayBuffer()` instead of accessing `response.audio`\n\n**Issue**: Generated audio file is empty or corrupted\n- **Solution**: Ensure you're calling `await response.arrayBuffer()` and properly converting to Buffer: `Buffer.from(new Uint8Array(arrayBuffer))`\n\n**Issue**: Audio sounds unnatural\n- **Solution**: Prepare text properly (remove special characters, expand abbreviations)\n\n**Issue**: Long processing times\n- **Solution**: Break long text into smaller chunks and process in parallel\n\n**Issue**: Next.js caching old API route\n- **Solution**: Create a new API route endpoint or restart the dev server\n\n## Performance Tips\n\n1. **Reuse SDK Instance**: Create ZAI instance once and reuse\n2. **Implement Caching**: Cache generated audio for repeated text\n3. **Batch Processing**: Process multiple texts efficiently\n4. **Optimize Text**: Remove unnecessary content before generation\n5. **Async Processing**: Use queues for handling multiple requests\n\n## Important Notes\n\n### API Constraints\n\n**Input Text Length**: Maximum 1024 characters per request. For longer text:\n```javascript\n\u002F\u002F Split long text into chunks\nconst longText = \"...\"; \u002F\u002F Your long text here\nconst chunks = splitTextIntoChunks(longText, 1000);\n\nfor (const chunk of chunks) {\n  const response = await zai.audio.tts.create({\n    input: chunk,\n    voice: 'tongtong',\n    speed: 1.0,\n    response_format: 'wav',\n    stream: false\n  });\n  \u002F\u002F Process each chunk...\n}\n```\n\n**Streaming Format Limitation**: When using `stream: true`, only `pcm` format is supported. For `wav` or `mp3` output, use `stream: false`.\n\n**Sample Rate**: Audio is generated at 24000 Hz sample rate (recommended setting for playback).\n\n### Response Object Format\n\nThe `zai.audio.tts.create()` method returns a standard **Response** object (not a custom object with an `audio` property). Always use:\n\n```javascript\n\u002F\u002F ✅ CORRECT\nconst response = await zai.audio.tts.create({ ... });\nconst arrayBuffer = await response.arrayBuffer();\nconst buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n\u002F\u002F ❌ WRONG - This will not work\nconst response = await zai.audio.tts.create({ ... });\nconst buffer = Buffer.from(response.audio); \u002F\u002F response.audio is undefined\n```\n\n### Available Voices\n\n- `tongtong` - 温暖亲切\n- `chuichui` - 活泼可爱\n- `xiaochen` - 沉稳专业\n- `jam` - 英音绅士\n- `kazi` - 清晰标准\n- `douji` - 自然流畅\n- `luodo` - 富有感染力\n\n### Speed Range\n\n- Minimum: `0.5` (half speed)\n- Default: `1.0` (normal speed)\n- Maximum: `2.0` (double speed)\n\n**Important**: Speed values outside the range [0.5, 2.0] will result in API errors.\n\n### Volume Range\n\n- Minimum: Greater than `0` (exclusive)\n- Default: `1.0` (normal volume)\n- Maximum: `10` (inclusive)\n\n**Note**: Volume parameter is optional. When not specified, defaults to 1.0.\n\n## Remember\n\n- Always use z-ai-web-dev-sdk in backend code only\n- **Input text is limited to 1024 characters maximum** - split longer text into chunks\n- **Speed must be between 0.5 and 2.0** - values outside this range will cause errors\n- **Volume must be greater than 0 and up to 10** - optional parameter with default 1.0\n- **Streaming only supports PCM format** - use non-streaming for WAV or MP3 output\n- The SDK returns a standard Response object - use `await response.arrayBuffer()`\n- Convert ArrayBuffer to Buffer using `Buffer.from(new Uint8Array(arrayBuffer))`\n- Handle audio buffers properly when saving to files\n- Implement error handling for production applications\n- Consider caching for frequently generated content\n- Clean up old audio files periodically to manage storage\n","# TTS (Text to Speech) Skill\n\nThis skill guides the implementation of text-to-speech (TTS) functionality using the z-ai-web-dev-sdk package, enabling conversion of text into natural-sounding speech audio.\n\n## Skills Path\n\n**Skill Location**: `{project_path}\u002Fskills\u002FTTS`\n\nThis skill is located at the above path in your project.\n\n**Reference Scripts**: Example test scripts are available in the `{Skill Location}\u002Fscripts\u002F` directory for quick testing and reference. See `{Skill Location}\u002Fscripts\u002Ftts.ts` for a working example.\n\n## Overview\n\nText-to-Speech allows you to build applications that generate spoken audio from text input, supporting various voices, speeds, and output formats for diverse use cases.\n\n**IMPORTANT**: z-ai-web-dev-sdk MUST be used in backend code only. Never use it in client-side code.\n\n## API Limitations and Constraints\n\nBefore implementing TTS functionality, be aware of these important limitations:\n\n### Input Text Constraints\n- **Maximum length**: 1024 characters per request\n- Text exceeding this limit must be split into smaller chunks\n\n### Audio Parameters\n- **Speed range**: 0.5 to 2.0\n  - 0.5 = half speed (slower)\n  - 1.0 = normal speed (default)\n  - 2.0 = double speed (faster)\n- **Volume range**: Greater than 0, up to 10\n  - Default: 1.0\n  - Values must be greater than 0 (exclusive) and up to 10 (inclusive)\n\n### Format and Streaming\n- **Streaming limitation**: When `stream: true` is enabled, only `pcm` format is supported\n- **Non-streaming**: Supports `wav`, `pcm`, and `mp3` formats\n- **Sample rate**: 24000 Hz (recommended)\n\n### Best Practice for Long Text\n```javascript\nfunction splitTextIntoChunks(text, maxLength = 1000) {\n  const chunks = [];\n  const sentences = text.match(\u002F[^.!?]+[.!?]+\u002Fg) || [text];\n  \n  let currentChunk = '';\n  for (const sentence of sentences) {\n    if ((currentChunk + sentence).length \u003C= maxLength) {\n      currentChunk += sentence;\n    } else {\n      if (currentChunk) chunks.push(currentChunk.trim());\n      currentChunk = sentence;\n    }\n  }\n  if (currentChunk) chunks.push(currentChunk.trim());\n  \n  return chunks;\n}\n```\n\n## Prerequisites\n\nThe z-ai-web-dev-sdk package is already installed. Import it as shown in the examples below.\n\n## CLI Usage (For Simple Tasks)\n\nFor simple text-to-speech conversions, you can use the z-ai CLI instead of writing code. This is ideal for quick audio generation, testing voices, or simple automation.\n\n### Basic TTS\n\n```bash\n# Convert text to speech (default WAV format)\nz-ai tts --input \"Hello, world\" --output .\u002Fhello.wav\n\n# Using short options\nz-ai tts -i \"Hello, world\" -o .\u002Fhello.wav\n```\n\n### Different Voices and Speed\n\n```bash\n# Use specific voice\nz-ai tts -i \"Welcome to our service\" -o .\u002Fwelcome.wav --voice tongtong\n\n# Adjust speech speed (0.5-2.0)\nz-ai tts -i \"This is faster speech\" -o .\u002Ffast.wav --speed 1.5\n\n# Slower speech\nz-ai tts -i \"This is slower speech\" -o .\u002Fslow.wav --speed 0.8\n```\n\n### Different Output Formats\n\n```bash\n# MP3 format\nz-ai tts -i \"Hello World\" -o .\u002Fhello.mp3 --format mp3\n\n# WAV format (default)\nz-ai tts -i \"Hello World\" -o .\u002Fhello.wav --format wav\n\n# PCM format\nz-ai tts -i \"Hello World\" -o .\u002Fhello.pcm --format pcm\n```\n\n### Streaming Output\n\n```bash\n# Stream audio generation\nz-ai tts -i \"This is a longer text that will be streamed\" -o .\u002Fstream.wav --stream\n```\n\n### CLI Parameters\n\n- `--input, -i \u003Ctext>`: **Required** - Text to convert to speech (max 1024 characters)\n- `--output, -o \u003Cpath>`: **Required** - Output audio file path\n- `--voice, -v \u003Cvoice>`: Optional - Voice type (default: tongtong)\n- `--speed, -s \u003Cnumber>`: Optional - Speech speed, 0.5-2.0 (default: 1.0)\n- `--format, -f \u003Cformat>`: Optional - Output format: wav, mp3, pcm (default: wav)\n- `--stream`: Optional - Enable streaming output (only supports pcm format)\n\n### When to Use CLI vs SDK\n\n**Use CLI for:**\n- Quick text-to-speech conversions\n- Testing different voices and speeds\n- Simple batch audio generation\n- Command-line automation scripts\n\n**Use SDK for:**\n- Dynamic audio generation in applications\n- Integration with web services\n- Custom audio processing pipelines\n- Production applications with complex requirements\n\n## Basic TTS Implementation\n\n### Simple Text to Speech\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function textToSpeech(text, outputPath) {\n  const zai = await ZAI.create();\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: 'tongtong',\n    speed: 1.0,\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  console.log(`Audio saved to ${outputPath}`);\n  return outputPath;\n}\n\n\u002F\u002F Usage\nawait textToSpeech('Hello, world!', '.\u002Foutput.wav');\n```\n\n### Multiple Voice Options\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function generateWithVoice(text, voice, outputPath) {\n  const zai = await ZAI.create();\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: voice, \u002F\u002F Available voices: tongtong, chuichui, xiaochen, jam, kazi, douji, luodo\n    speed: 1.0,\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  return outputPath;\n}\n\n\u002F\u002F Usage\nawait generateWithVoice('Welcome to our service', 'tongtong', '.\u002Fwelcome.wav');\n```\n\n### Adjustable Speed\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function generateWithSpeed(text, speed, outputPath) {\n  const zai = await ZAI.create();\n\n  \u002F\u002F Speed range: 0.5 to 2.0 (API constraint)\n  \u002F\u002F 0.5 = half speed (slower)\n  \u002F\u002F 1.0 = normal speed (default)\n  \u002F\u002F 2.0 = double speed (faster)\n  \u002F\u002F Values outside this range will cause API errors\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: 'tongtong',\n    speed: speed,\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  return outputPath;\n}\n\n\u002F\u002F Usage - slower narration\nawait generateWithSpeed('This is an important announcement', 0.8, '.\u002Fslow.wav');\n\n\u002F\u002F Usage - faster narration\nawait generateWithSpeed('Quick update', 1.3, '.\u002Ffast.wav');\n```\n\n### Adjustable Volume\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function generateWithVolume(text, volume, outputPath) {\n  const zai = await ZAI.create();\n\n  \u002F\u002F Volume range: greater than 0, up to 10 (API constraint)\n  \u002F\u002F Values must be > 0 (exclusive) and \u003C= 10 (inclusive)\n  \u002F\u002F Default: 1.0 (normal volume)\n\n  const response = await zai.audio.tts.create({\n    input: text,\n    voice: 'tongtong',\n    speed: 1.0,\n    volume: volume, \u002F\u002F Optional parameter\n    response_format: 'wav',\n    stream: false\n  });\n\n  \u002F\u002F Get array buffer from Response object\n  const arrayBuffer = await response.arrayBuffer();\n  const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n  fs.writeFileSync(outputPath, buffer);\n  return outputPath;\n}\n\n\u002F\u002F Usage - louder audio\nawait generateWithVolume('This is an announcement', 5.0, '.\u002Floud.wav');\n\n\u002F\u002F Usage - quieter audio\nawait generateWithVolume('Whispered message', 0.5, '.\u002Fquiet.wav');\n```\n\n## Advanced Use Cases\n\n### Batch Processing\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\nimport path from 'path';\n\nasync function batchTextToSpeech(textArray, outputDir) {\n  const zai = await ZAI.create();\n  const results = [];\n\n  \u002F\u002F Ensure output directory exists\n  if (!fs.existsSync(outputDir)) {\n    fs.mkdirSync(outputDir, { recursive: true });\n  }\n\n  for (let i = 0; i \u003C textArray.length; i++) {\n    try {\n      const text = textArray[i];\n      const outputPath = path.join(outputDir, `audio_${i + 1}.wav`);\n\n      const response = await zai.audio.tts.create({\n        input: text,\n        voice: 'tongtong',\n        speed: 1.0,\n        response_format: 'wav',\n        stream: false\n      });\n\n      \u002F\u002F Get array buffer from Response object\n      const arrayBuffer = await response.arrayBuffer();\n      const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n      fs.writeFileSync(outputPath, buffer);\n      results.push({\n        success: true,\n        text,\n        path: outputPath\n      });\n    } catch (error) {\n      results.push({\n        success: false,\n        text: textArray[i],\n        error: error.message\n      });\n    }\n  }\n\n  return results;\n}\n\n\u002F\u002F Usage\nconst texts = [\n  'Welcome to chapter one',\n  'Welcome to chapter two',\n  'Welcome to chapter three'\n];\n\nconst results = await batchTextToSpeech(texts, '.\u002Faudio-output');\nconsole.log('Generated:', results.length, 'audio files');\n```\n\n### Dynamic Content Generation\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nclass TTSGenerator {\n  constructor() {\n    this.zai = null;\n  }\n\n  async initialize() {\n    this.zai = await ZAI.create();\n  }\n\n  async generateAudio(text, options = {}) {\n    const {\n      voice = 'tongtong',\n      speed = 1.0,\n      format = 'wav'\n    } = options;\n\n    const response = await this.zai.audio.tts.create({\n      input: text,\n      voice: voice,\n      speed: speed,\n      response_format: format,\n      stream: false\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    return Buffer.from(new Uint8Array(arrayBuffer));\n  }\n\n  async saveAudio(text, outputPath, options = {}) {\n    const buffer = await this.generateAudio(text, options);\n    if (buffer) {\n      fs.writeFileSync(outputPath, buffer);\n      return outputPath;\n    }\n    return null;\n  }\n}\n\n\u002F\u002F Usage\nconst generator = new TTSGenerator();\nawait generator.initialize();\n\nawait generator.saveAudio(\n  'Hello, this is a test',\n  '.\u002Foutput.wav',\n  { speed: 1.2 }\n);\n```\n\n### Next.js API Route Example\n\n```javascript\nimport { NextRequest, NextResponse } from 'next\u002Fserver';\n\nexport async function POST(req: NextRequest) {\n  try {\n    const { text, voice = 'tongtong', speed = 1.0 } = await req.json();\n\n    \u002F\u002F Import ZAI SDK\n    const ZAI = (await import('z-ai-web-dev-sdk')).default;\n\n    \u002F\u002F Create SDK instance\n    const zai = await ZAI.create();\n\n    \u002F\u002F Generate TTS audio\n    const response = await zai.audio.tts.create({\n      input: text.trim(),\n      voice: voice,\n      speed: speed,\n      response_format: 'wav',\n      stream: false,\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n    \u002F\u002F Return audio as response\n    return new NextResponse(buffer, {\n      status: 200,\n      headers: {\n        'Content-Type': 'audio\u002Fwav',\n        'Content-Length': buffer.length.toString(),\n        'Cache-Control': 'no-cache',\n      },\n    });\n  } catch (error) {\n    console.error('TTS API Error:', error);\n\n    return NextResponse.json(\n      {\n        error: error instanceof Error ? error.message : '生成语音失败，请稍后重试',\n      },\n      { status: 500 }\n    );\n  }\n}\n```\n\n## Best Practices\n\n### 1. Text Preparation\n```javascript\nfunction prepareTextForTTS(text) {\n  \u002F\u002F Remove excessive whitespace\n  text = text.replace(\u002F\\s+\u002Fg, ' ').trim();\n\n  \u002F\u002F Expand common abbreviations for better pronunciation\n  const abbreviations = {\n    'Dr.': 'Doctor',\n    'Mr.': 'Mister',\n    'Mrs.': 'Misses',\n    'etc.': 'et cetera'\n  };\n\n  for (const [abbr, full] of Object.entries(abbreviations)) {\n    text = text.replace(new RegExp(abbr, 'g'), full);\n  }\n\n  return text;\n}\n```\n\n### 2. Error Handling\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\n\nasync function safeTTS(text, outputPath) {\n  try {\n    \u002F\u002F Validate input\n    if (!text || text.trim().length === 0) {\n      throw new Error('Text input cannot be empty');\n    }\n\n    if (text.length > 1024) {\n      throw new Error('Text input exceeds maximum length of 1024 characters');\n    }\n\n    const zai = await ZAI.create();\n\n    const response = await zai.audio.tts.create({\n      input: text,\n      voice: 'tongtong',\n      speed: 1.0,\n      response_format: 'wav',\n      stream: false\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n    fs.writeFileSync(outputPath, buffer);\n\n    return {\n      success: true,\n      path: outputPath,\n      size: buffer.length\n    };\n  } catch (error) {\n    console.error('TTS Error:', error);\n    return {\n      success: false,\n      error: error.message\n    };\n  }\n}\n```\n\n### 3. SDK Instance Reuse\n\n```javascript\nimport ZAI from 'z-ai-web-dev-sdk';\n\n\u002F\u002F Create a singleton instance\nlet zaiInstance = null;\n\nasync function getZAIInstance() {\n  if (!zaiInstance) {\n    zaiInstance = await ZAI.create();\n  }\n  return zaiInstance;\n}\n\n\u002F\u002F Usage\nconst zai = await getZAIInstance();\nconst response = await zai.audio.tts.create({ ... });\n```\n\n## Common Use Cases\n\n1. **Audiobooks & Podcasts**: Convert written content to audio format\n2. **E-learning**: Create narration for educational content\n3. **Accessibility**: Provide audio versions of text content\n4. **Voice Assistants**: Generate dynamic responses\n5. **Announcements**: Create automated audio notifications\n6. **IVR Systems**: Generate phone system prompts\n7. **Content Localization**: Create audio in different languages\n\n## Integration Examples\n\n### Express.js API Endpoint\n\n```javascript\nimport express from 'express';\nimport ZAI from 'z-ai-web-dev-sdk';\nimport fs from 'fs';\nimport path from 'path';\n\nconst app = express();\napp.use(express.json());\n\nlet zaiInstance;\nconst outputDir = '.\u002Faudio-output';\n\nasync function initZAI() {\n  zaiInstance = await ZAI.create();\n  if (!fs.existsSync(outputDir)) {\n    fs.mkdirSync(outputDir, { recursive: true });\n  }\n}\n\napp.post('\u002Fapi\u002Ftts', async (req, res) => {\n  try {\n    const { text, voice = 'tongtong', speed = 1.0 } = req.body;\n\n    if (!text) {\n      return res.status(400).json({ error: 'Text is required' });\n    }\n\n    const filename = `tts_${Date.now()}.wav`;\n    const outputPath = path.join(outputDir, filename);\n\n    const response = await zaiInstance.audio.tts.create({\n      input: text,\n      voice: voice,\n      speed: speed,\n      response_format: 'wav',\n      stream: false\n    });\n\n    \u002F\u002F Get array buffer from Response object\n    const arrayBuffer = await response.arrayBuffer();\n    const buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n    fs.writeFileSync(outputPath, buffer);\n\n    res.json({\n      success: true,\n      audioUrl: `\u002Faudio\u002F${filename}`,\n      size: buffer.length\n    });\n  } catch (error) {\n    res.status(500).json({ error: error.message });\n  }\n});\n\napp.use('\u002Faudio', express.static('audio-output'));\n\ninitZAI().then(() => {\n  app.listen(3000, () => {\n    console.log('TTS API running on port 3000');\n  });\n});\n```\n\n## Troubleshooting\n\n**Issue**: \"Input text exceeds maximum length\"\n- **Solution**: Text input is limited to 1024 characters. Split longer text into chunks using the `splitTextIntoChunks` function shown in the API Limitations section\n\n**Issue**: \"Invalid speed parameter\" or unexpected speed behavior\n- **Solution**: Speed must be between 0.5 and 2.0. Check your speed value is within this range\n\n**Issue**: \"Invalid volume parameter\"\n- **Solution**: Volume must be greater than 0 and up to 10. Ensure volume value is in range (0, 10]\n\n**Issue**: \"Stream format not supported\" with WAV\u002FMP3\n- **Solution**: Streaming mode only supports PCM format. Either use `response_format: 'pcm'` with streaming, or disable streaming (`stream: false`) for WAV\u002FMP3 output\n\n**Issue**: \"SDK must be used in backend\"\n- **Solution**: Ensure z-ai-web-dev-sdk is only imported in server-side code\n\n**Issue**: \"TypeError: response.audio is undefined\"\n- **Solution**: The SDK returns a standard Response object, use `await response.arrayBuffer()` instead of accessing `response.audio`\n\n**Issue**: Generated audio file is empty or corrupted\n- **Solution**: Ensure you're calling `await response.arrayBuffer()` and properly converting to Buffer: `Buffer.from(new Uint8Array(arrayBuffer))`\n\n**Issue**: Audio sounds unnatural\n- **Solution**: Prepare text properly (remove special characters, expand abbreviations)\n\n**Issue**: Long processing times\n- **Solution**: Break long text into smaller chunks and process in parallel\n\n**Issue**: Next.js caching old API route\n- **Solution**: Create a new API route endpoint or restart the dev server\n\n## Performance Tips\n\n1. **Reuse SDK Instance**: Create ZAI instance once and reuse\n2. **Implement Caching**: Cache generated audio for repeated text\n3. **Batch Processing**: Process multiple texts efficiently\n4. **Optimize Text**: Remove unnecessary content before generation\n5. **Async Processing**: Use queues for handling multiple requests\n\n## Important Notes\n\n### API Constraints\n\n**Input Text Length**: Maximum 1024 characters per request. For longer text:\n```javascript\n\u002F\u002F Split long text into chunks\nconst longText = \"...\"; \u002F\u002F Your long text here\nconst chunks = splitTextIntoChunks(longText, 1000);\n\nfor (const chunk of chunks) {\n  const response = await zai.audio.tts.create({\n    input: chunk,\n    voice: 'tongtong',\n    speed: 1.0,\n    response_format: 'wav',\n    stream: false\n  });\n  \u002F\u002F Process each chunk...\n}\n```\n\n**Streaming Format Limitation**: When using `stream: true`, only `pcm` format is supported. For `wav` or `mp3` output, use `stream: false`.\n\n**Sample Rate**: Audio is generated at 24000 Hz sample rate (recommended setting for playback).\n\n### Response Object Format\n\nThe `zai.audio.tts.create()` method returns a standard **Response** object (not a custom object with an `audio` property). Always use:\n\n```javascript\n\u002F\u002F ✅ CORRECT\nconst response = await zai.audio.tts.create({ ... });\nconst arrayBuffer = await response.arrayBuffer();\nconst buffer = Buffer.from(new Uint8Array(arrayBuffer));\n\n\u002F\u002F ❌ WRONG - This will not work\nconst response = await zai.audio.tts.create({ ... });\nconst buffer = Buffer.from(response.audio); \u002F\u002F response.audio is undefined\n```\n\n### Available Voices\n\n- `tongtong` - 温暖亲切\n- `chuichui` - 活泼可爱\n- `xiaochen` - 沉稳专业\n- `jam` - 英音绅士\n- `kazi` - 清晰标准\n- `douji` - 自然流畅\n- `luodo` - 富有感染力\n\n### Speed Range\n\n- Minimum: `0.5` (half speed)\n- Default: `1.0` (normal speed)\n- Maximum: `2.0` (double speed)\n\n**Important**: Speed values outside the range [0.5, 2.0] will result in API errors.\n\n### Volume Range\n\n- Minimum: Greater than `0` (exclusive)\n- Default: `1.0` (normal volume)\n- Maximum: `10` (inclusive)\n\n**Note**: Volume parameter is optional. When not specified, defaults to 1.0.\n\n## Remember\n\n- Always use z-ai-web-dev-sdk in backend code only\n- **Input text is limited to 1024 characters maximum** - split longer text into chunks\n- **Speed must be between 0.5 and 2.0** - values outside this range will cause errors\n- **Volume must be greater than 0 and up to 10** - optional parameter with default 1.0\n- **Streaming only supports PCM format** - use non-streaming for WAV or MP3 output\n- The SDK returns a standard Response object - use `await response.arrayBuffer()`\n- Convert ArrayBuffer to Buffer using `Buffer.from(new Uint8Array(arrayBuffer))`\n- Handle audio buffers properly when saving to files\n- Implement error handling for production applications\n- Consider caching for frequently generated content\n- Clean up old audio files periodically to manage storage\n",{"name":5,"license":14,"description":7},"main","7d045d4d6ec778ab8575aad8f8a7e7e7d4321918","skills\u002FTTS","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video","https:\u002F\u002Fgithub.com\u002Fnordeim","A freelance IT engineer","2026-07-06 19:57:32",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add nordeim\u002Fstory-into-video --skill TTS",{"tool":37,"command":38},"bunx","bunx skills add nordeim\u002Fstory-into-video --skill TTS",{"tool":40,"command":41},"pnpm","pnpm dlx skills add nordeim\u002Fstory-into-video --skill TTS","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002FTTS\u002FSKILL.md",true,[45,50],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":15},"LICENSE.txt","LICENSE","许可证",1080,{"path":51,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":55},"tts.ts","SCRIPT","脚本",656,"https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002FTTS\u002Ftts.ts",[57,66,74,82,89,97],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":62,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M77Q7YD61R8X6JKW9F3N07PN","webapp-testing","Web application testing principles. E2E, Playwright, deep audit strategies.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M77Q7AMJRHTJ41DFBTP7TSPF","web-search","Implement web search capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to search for real-time information from the web, retrieve up-to-date content beyond the knowledge cutoff, or find the latest news and data. Returns structured search results with URLs, snippets, and metadata.","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fweb-search\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fweb-search\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":78,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M77Q74VD9G7H0HYYDA39NS7G","web-reader","Implement web page content extraction capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to scrape web pages, extract article content, retrieve page metadata, or build applications that process web content. Supports automatic content extraction with title, HTML, and publication time retrieval.","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fweb-reader\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fweb-reader\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M77Q6WY2DJZV5DQTMYKN9PVF","web-frameworks","Build modern full-stack web applications with Next.js 16 + React 19 (App Router, Server Components, RSC, PPR, cacheComponents, async params, SSR, SSG, ISR, standalone output), Turborepo (monorepo, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons). Use when creating React applications, implementing server-side rendering, setting up monorepos, optimizing build performance and caching, or working with TypeScript full-stack projects.","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fweb-frameworks\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M77Q6DD51GTZG7N68PSSSZ49","video-understand","Implement specialized video understanding capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze video content, understand motion and temporal sequences, extract information from video frames, describe video scenes, or perform video-based AI analysis. Optimized for MP4, AVI, MOV, and other common video formats.","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-understand\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-understand\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M77Q667DHYZWHXQGB2MJDRA4","video-generation","Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generation\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fnordeim\u002Fstory-into-video\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-generation\u002FSKILL.md",[],[]]