[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XEHH2XVQ04RHG07KXG5F5N":3,"skill-same:01M6XEHH2XVQ04RHG07KXG5F5N":58},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":13,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":6,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M6XEHH2XVQ04RHG07KXG5F5N","openai-tts",null,"OpenAI Text-to-Speech API for high-quality speech synthesis. Use for generating natural-sounding audio from text with customizable voices and tones.","Waaaalnut\u002Fskillsbench","Waaaalnut","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F103995656?v=4","01M6XCS9K1V51EY3JMB7DGMX24","01M6XCS9Q4WPW88W62C55G1H44",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fpg-essay-to-audiobook\u002Fenvironment\u002Fskills\u002Fopenai-tts\u002FSKILL.md",[],[18,19,20,21,22,23,24,25,26,27,28,29,30,31],"openai","tts","openai tts","speech","api","Audio","text","quality","use","Synthesis","with","text-to-speech","high","for","2026-11-10 10:12:30",false,"---\nname: openai-tts\ndescription: \"OpenAI Text-to-Speech API for high-quality speech synthesis. Use for generating natural-sounding audio from text with customizable voices and tones.\"\n---\n\n# OpenAI Text-to-Speech\n\nGenerate high-quality spoken audio from text using OpenAI's TTS API.\n\n## Authentication\n\nThe API key is available as environment variable:\n```bash\nOPENAI_API_KEY\n```\n\n## Models\n\n- `gpt-4o-mini-tts` - Newest, most reliable. Supports tone\u002Fstyle instructions.\n- `tts-1` - Lower latency, lower quality\n- `tts-1-hd` - Higher quality, higher latency\n\n## Voice Options\n\nBuilt-in voices (English optimized):\n- `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`\n- `nova`, `onyx`, `sage`, `shimmer`, `verse`\n- `marin`, `cedar` - **Recommended for best quality**\n\nNote: `tts-1` and `tts-1-hd` only support: alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer.\n\n## Python Example\n\n```python\nfrom pathlib import Path\nfrom openai import OpenAI\n\nclient = OpenAI()  # Uses OPENAI_API_KEY env var\n\n# Basic usage\nwith client.audio.speech.with_streaming_response.create(\n    model=\"gpt-4o-mini-tts\",\n    voice=\"coral\",\n    input=\"Hello, world!\",\n) as response:\n    response.stream_to_file(\"output.mp3\")\n\n# With tone instructions (gpt-4o-mini-tts only)\nwith client.audio.speech.with_streaming_response.create(\n    model=\"gpt-4o-mini-tts\",\n    voice=\"coral\",\n    input=\"Today is a wonderful day!\",\n    instructions=\"Speak in a cheerful and positive tone.\",\n) as response:\n    response.stream_to_file(\"output.mp3\")\n```\n\n## Handling Long Text\n\nFor long documents, split into chunks and concatenate:\n\n```python\nfrom openai import OpenAI\nfrom pydub import AudioSegment\nimport tempfile\nimport re\nimport os\n\nclient = OpenAI()\n\ndef chunk_text(text, max_chars=4000):\n    \"\"\"Split text into chunks at sentence boundaries.\"\"\"\n    sentences = re.split(r'(?\u003C=[.!?])\\s+', text)\n    chunks = []\n    current_chunk = \"\"\n\n    for sentence in sentences:\n        if len(current_chunk) + len(sentence) \u003C max_chars:\n            current_chunk += sentence + \" \"\n        else:\n            if current_chunk:\n                chunks.append(current_chunk.strip())\n            current_chunk = sentence + \" \"\n\n    if current_chunk:\n        chunks.append(current_chunk.strip())\n\n    return chunks\n\ndef text_to_audiobook(text, output_path):\n    \"\"\"Convert long text to audio file.\"\"\"\n    chunks = chunk_text(text)\n    audio_segments = []\n\n    for chunk in chunks:\n        with tempfile.NamedTemporaryFile(suffix='.mp3', delete=False) as tmp:\n            tmp_path = tmp.name\n\n        with client.audio.speech.with_streaming_response.create(\n            model=\"gpt-4o-mini-tts\",\n            voice=\"coral\",\n            input=chunk,\n        ) as response:\n            response.stream_to_file(tmp_path)\n\n        segment = AudioSegment.from_mp3(tmp_path)\n        audio_segments.append(segment)\n        os.unlink(tmp_path)\n\n    # Concatenate all segments\n    combined = audio_segments[0]\n    for segment in audio_segments[1:]:\n        combined += segment\n\n    combined.export(output_path, format=\"mp3\")\n```\n\n## Output Formats\n\n- `mp3` - Default, general use\n- `opus` - Low latency streaming\n- `aac` - Digital compression (YouTube, iOS)\n- `flac` - Lossless compression\n- `wav` - Uncompressed, low latency\n- `pcm` - Raw samples (24kHz, 16-bit)\n\n```python\nwith client.audio.speech.with_streaming_response.create(\n    model=\"gpt-4o-mini-tts\",\n    voice=\"coral\",\n    input=\"Hello!\",\n    response_format=\"wav\",  # Specify format\n) as response:\n    response.stream_to_file(\"output.wav\")\n```\n\n## Best Practices\n\n- Use `marin` or `cedar` voices for best quality\n- Split text at sentence boundaries for long content\n- Use `wav` or `pcm` for lowest latency\n- Add `instructions` parameter to control tone\u002Fstyle (gpt-4o-mini-tts only)\n","# OpenAI Text-to-Speech\n\nGenerate high-quality spoken audio from text using OpenAI's TTS API.\n\n## Authentication\n\nThe API key is available as environment variable:\n```bash\nOPENAI_API_KEY\n```\n\n## Models\n\n- `gpt-4o-mini-tts` - Newest, most reliable. Supports tone\u002Fstyle instructions.\n- `tts-1` - Lower latency, lower quality\n- `tts-1-hd` - Higher quality, higher latency\n\n## Voice Options\n\nBuilt-in voices (English optimized):\n- `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`\n- `nova`, `onyx`, `sage`, `shimmer`, `verse`\n- `marin`, `cedar` - **Recommended for best quality**\n\nNote: `tts-1` and `tts-1-hd` only support: alloy, ash, coral, echo, fable, onyx, nova, sage, shimmer.\n\n## Python Example\n\n```python\nfrom pathlib import Path\nfrom openai import OpenAI\n\nclient = OpenAI()  # Uses OPENAI_API_KEY env var\n\n# Basic usage\nwith client.audio.speech.with_streaming_response.create(\n    model=\"gpt-4o-mini-tts\",\n    voice=\"coral\",\n    input=\"Hello, world!\",\n) as response:\n    response.stream_to_file(\"output.mp3\")\n\n# With tone instructions (gpt-4o-mini-tts only)\nwith client.audio.speech.with_streaming_response.create(\n    model=\"gpt-4o-mini-tts\",\n    voice=\"coral\",\n    input=\"Today is a wonderful day!\",\n    instructions=\"Speak in a cheerful and positive tone.\",\n) as response:\n    response.stream_to_file(\"output.mp3\")\n```\n\n## Handling Long Text\n\nFor long documents, split into chunks and concatenate:\n\n```python\nfrom openai import OpenAI\nfrom pydub import AudioSegment\nimport tempfile\nimport re\nimport os\n\nclient = OpenAI()\n\ndef chunk_text(text, max_chars=4000):\n    \"\"\"Split text into chunks at sentence boundaries.\"\"\"\n    sentences = re.split(r'(?\u003C=[.!?])\\s+', text)\n    chunks = []\n    current_chunk = \"\"\n\n    for sentence in sentences:\n        if len(current_chunk) + len(sentence) \u003C max_chars:\n            current_chunk += sentence + \" \"\n        else:\n            if current_chunk:\n                chunks.append(current_chunk.strip())\n            current_chunk = sentence + \" \"\n\n    if current_chunk:\n        chunks.append(current_chunk.strip())\n\n    return chunks\n\ndef text_to_audiobook(text, output_path):\n    \"\"\"Convert long text to audio file.\"\"\"\n    chunks = chunk_text(text)\n    audio_segments = []\n\n    for chunk in chunks:\n        with tempfile.NamedTemporaryFile(suffix='.mp3', delete=False) as tmp:\n            tmp_path = tmp.name\n\n        with client.audio.speech.with_streaming_response.create(\n            model=\"gpt-4o-mini-tts\",\n            voice=\"coral\",\n            input=chunk,\n        ) as response:\n            response.stream_to_file(tmp_path)\n\n        segment = AudioSegment.from_mp3(tmp_path)\n        audio_segments.append(segment)\n        os.unlink(tmp_path)\n\n    # Concatenate all segments\n    combined = audio_segments[0]\n    for segment in audio_segments[1:]:\n        combined += segment\n\n    combined.export(output_path, format=\"mp3\")\n```\n\n## Output Formats\n\n- `mp3` - Default, general use\n- `opus` - Low latency streaming\n- `aac` - Digital compression (YouTube, iOS)\n- `flac` - Lossless compression\n- `wav` - Uncompressed, low latency\n- `pcm` - Raw samples (24kHz, 16-bit)\n\n```python\nwith client.audio.speech.with_streaming_response.create(\n    model=\"gpt-4o-mini-tts\",\n    voice=\"coral\",\n    input=\"Hello!\",\n    response_format=\"wav\",  # Specify format\n) as response:\n    response.stream_to_file(\"output.wav\")\n```\n\n## Best Practices\n\n- Use `marin` or `cedar` voices for best quality\n- Split text at sentence boundaries for long content\n- Use `wav` or `pcm` for lowest latency\n- Add `instructions` parameter to control tone\u002Fstyle (gpt-4o-mini-tts only)\n",{"name":5,"description":7},"main","7eeb258ada72b7f58119b0e7a2c00ea89d9beedd","tasks\u002Fpg-essay-to-audiobook\u002Fenvironment\u002Fskills\u002Fopenai-tts","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench","https:\u002F\u002Fgithub.com\u002FWaaaalnut","student of Zhejiang University","2026-04-21 23:16:23",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add Waaaalnut\u002Fskillsbench --skill openai-tts",{"tool":50,"command":51},"bunx","bunx skills add Waaaalnut\u002Fskillsbench --skill openai-tts",{"tool":53,"command":54},"pnpm","pnpm dlx skills add Waaaalnut\u002Fskillsbench --skill openai-tts","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fpg-essay-to-audiobook\u002Fenvironment\u002Fskills\u002Fopenai-tts\u002FSKILL.md",true,[],[59,73,86,113,134,152],{"skillNo":60,"name":61,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":69,"publishedAt":32},"01M6XEWMJ6VY3ZC53MPDCPG3GH","data-reconciliation","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fxlsx-recover-data\u002Fenvironment\u002Fskills\u002Fdata-reconciliation\u002FSKILL.md",[64],{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[70,71,72],"data reconciliation","reconciliation","data",{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":32},"01M6XEW8MNPMF1KRXV6ATGFRQF","speech-to-text","Transcribe video to timestamped text using Whisper tiny model (pre-installed).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-tutorial-indexer\u002Fenvironment\u002Fskills\u002Fspeech-to-text\u002FSKILL.md",[],[21,24,80,81,82,83,84,85],"speech to text","transcribe video","whisper","model","Video","transcribe",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":97,"publishedAt":32},"01M6XEW3FQZP0T1RKQQJFXVY9T","video-processor","Process videos by removing segments and concatenating remaining parts. Use when you need to remove detected pauses\u002Fopenings from videos, create highlight reels, or batch process segment removals using ffmpeg filter_complex.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fvideo-processor\u002FSKILL.md",[92],{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[84,98,99,100,101,102,103,104,105,106,107,108,109,110,111,26,112],"processor","video processor","batch","create","reels","when","parts","segments","process","videos","you","segment","filter","ffmpeg","remove",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":32},"01M6XEVXJ5KZ0NTY3XZKRY4AS1","silence-detector","Detect initial silence segments in audio\u002Fvideo using energy-based analysis. Use when you need to find low-energy periods at the start of recordings (title slides, setup time, pre-roll silence).","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsilence-detector\u002FSKILL.md",[119],{"categoryNo":93,"categoryName":94,"taxonomyType":95,"taxonomyTypeDesc":96},[121,122,123,124,103,108,125,126,127,128,129,105,130,23,84,131,132,133,26],"detector","silence detector","title","slides","time","energy","at","recordings","detect","find","analysis","start","setup",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":140,"publishedAt":32},"01M6XEVT3NGRN1FT7JPMAPXS6M","segment-combiner","Combine multiple segment detection results into a unified list. Use when you need to merge segments from different detectors, prepare removal lists for video processing, or consolidate detection outputs.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Fsegment-combiner\u002FSKILL.md",[],[109,141,84,142,143,144,145,31,103,146,147,105,108,148,149,26,150,151],"segment combiner","detection","prepare","merge","video processing","outputs","combine","processing","consolidate","results","list",{"skillNo":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":161,"publishedAt":32},"01M6XEVMPVASGS2KX86QK4FMT7","report-generator","Generate compression reports for video processing. Use when you need to create structured JSON reports with duration statistics, compression ratios, and segment details after video processing.","https:\u002F\u002Fgithub.com\u002FWaaaalnut\u002Fskillsbench\u002Fblob\u002Fmain\u002Ftasks\u002Fvideo-silence-remover\u002Fenvironment\u002Fskills\u002Freport-generator\u002FSKILL.md",[158],{"categoryNo":159,"categoryName":160,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000034","行政与办公人员",[162,163,164,109,103,31,108,28,148,165,166,167,26,145,168,84,169,170,101],"generator","report generator","report","statistics","structured","reports","json","compression","generate"]