{"id":"53f9f455-4d57-499e-8da6-cbfddedfaa59","shortId":"wVHyzy","kind":"skill","title":"Whisper.cpp Real-Time Transcription Pipeline","tagline":"Streams audio from PulseAudio or ALSA devices into whisper.cpp for real-time speech-to-text with word-level timestamps. Outputs SRT/VTT subtitles and JSON transcripts simultaneously.","description":"# Whisper.cpp Real-Time Transcription Pipeline\n\nStreams audio from PulseAudio or ALSA devices into whisper.cpp for real-time speech-to-text with word-level timestamps. Outputs SRT/VTT subtitles and JSON transcripts simultaneously.\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- pip install -U openai-whisper\n- pip install git+https://github.com/openai/whisper.git\n- pip install --upgrade --no-deps --force-reinstall git+https://github.com/openai/whisper.git\n- brew install ffmpeg\n\nRequirements and caveats from upstream:\n- We used Python 3.9.9 and [PyTorch](https://pytorch.org/) 1.10.1 to train and test our models, but the codebase is expected to be compatible with Python 3.8-3.11 and recent PyTorch versions. The codebase also depends o...\n- Alternatively, the following command will pull and install the latest commit from this repository, along with its Python dependencies:\n- It also requires the command-line tool [ffmpeg](https://ffmpeg.org/) to be installed on your system, which is available from most package managers:\n\nBasic usage or getting-started notes:\n- [[Colab example]](https://colab.research.google.com/github/openai/whisper/blob/master/notebooks/LibriSpeech.ipynb)\n- To update the package to the latest version of this repository, please run:\n- bash\n\n- Source: https://github.com/openai/whisper\n- Extracted from upstream docs: https://raw.githubusercontent.com/openai/whisper/HEAD/README.md\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/whisper-cpp-realtime-transcription-pipeline/)","tags":["whisper","cpp","realtime","transcription","pipeline","skills","agentskillexchange","agent-skills","ai-agents","ai-tools","awesome-list","claude-code"],"capabilities":["skill","source-agentskillexchange","skill-whisper-cpp-realtime-transcription-pipeline","topic-agent-skills","topic-ai-agents","topic-ai-tools","topic-awesome-list","topic-claude-code","topic-codex","topic-cursor","topic-llm","topic-mcp","topic-npx-skills","topic-openclaw","topic-skills-catalog"],"categories":["skills"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/agentskillexchange/skills/whisper-cpp-realtime-transcription-pipeline","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add agentskillexchange/skills","source_repo":"https://github.com/agentskillexchange/skills","install_from":"skills.sh"}},"qualityScore":"0.454","qualityRationale":"deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,576 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-18T19:13:05.482Z","embedding":null,"createdAt":"2026-05-18T13:20:18.013Z","updatedAt":"2026-05-18T19:13:05.482Z","lastSeenAt":"2026-05-18T19:13:05.482Z","tsv":"'-3.11':143 '/)':124,183 '/github/openai/whisper/blob/master/notebooks/librispeech.ipynb)':208 '/openai/whisper':226 '/openai/whisper.git':94,107 '/openai/whisper/head/readme.md':233 '/skills/whisper-cpp-realtime-transcription-pipeline/)':240 '1.10.1':125 '3.8':142 '3.9.9':119 'agent':235 'agentskillexchange.com':239 'agentskillexchange.com/skills/whisper-cpp-realtime-transcription-pipeline/)':238 'along':167 'alsa':12,47 'also':150,173 'altern':153 'audio':8,43 'avail':192 'bash':222 'basic':197 'brew':108 'caveat':113 'codebas':134,149 'colab':204 'colab.research.google.com':207 'colab.research.google.com/github/openai/whisper/blob/master/notebooks/librispeech.ipynb)':206 'command':156,177 'command-lin':176 'commit':163 'compat':139 'dep':100 'depend':151,171 'devic':13,48 'doc':230 'environ':82 'exampl':205 'exchang':237 'expect':136 'extract':227 'ffmpeg':110,180 'ffmpeg.org':182 'ffmpeg.org/)':181 'follow':155 'forc':102 'force-reinstal':101 'get':201 'getting-start':200 'git':91,104 'github.com':93,106,225 'github.com/openai/whisper':224 'github.com/openai/whisper.git':92,105 'instal':71,75,84,90,96,109,160,186 'json':33,68 'latest':162,215 'level':27,62 'line':178 'manag':196 'match':80 'model':131 'no-dep':98 'note':203 'o':152 'openai':87 'openai-whisp':86 'output':29,64 'packag':195,212 'path':78 'pip':83,89,95 'pipelin':6,41 'pleas':220 'pull':158 'pulseaudio':10,45 'python':118,141,170 'pytorch':121,146 'pytorch.org':123 'pytorch.org/)':122 'raw.githubusercontent.com':232 'raw.githubusercontent.com/openai/whisper/head/readme.md':231 'real':3,18,38,53 'real-tim':2,17,37,52 'recent':145 'reinstal':103 'repositori':166,219 'requir':111,174 'run':221 'setup':77 'simultan':35,70 'skill':236 'skill-whisper-cpp-realtime-transcription-pipeline' 'sourc':223,234 'source-agentskillexchange' 'speech':21,56 'speech-to-text':20,55 'srt/vtt':30,65 'start':202 'stream':7,42 'subtitl':31,66 'system':189 'test':129 'text':23,58 'time':4,19,39,54 'timestamp':28,63 'tool':179 'topic-agent-skills' 'topic-ai-agents' 'topic-ai-tools' 'topic-awesome-list' 'topic-claude-code' 'topic-codex' 'topic-cursor' 'topic-llm' 'topic-mcp' 'topic-npx-skills' 'topic-openclaw' 'topic-skills-catalog' 'train':127 'transcript':5,34,40,69 'u':85 'updat':210 'upgrad':97 'upstream':74,115,229 'usag':198 'use':72,117 'version':147,216 'whisper':88 'whisper.cpp':1,15,36,50 'word':26,61 'word-level':25,60","prices":[{"id":"95074549-0f3c-44e9-938b-4f953b0db517","listingId":"53f9f455-4d57-499e-8da6-cbfddedfaa59","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"agentskillexchange","category":"skills","install_from":"skills.sh"},"createdAt":"2026-05-18T13:20:18.013Z"}],"sources":[{"listingId":"53f9f455-4d57-499e-8da6-cbfddedfaa59","source":"github","sourceId":"agentskillexchange/skills/whisper-cpp-realtime-transcription-pipeline","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/whisper-cpp-realtime-transcription-pipeline","isPrimary":false,"firstSeenAt":"2026-05-18T13:20:18.013Z","lastSeenAt":"2026-05-18T19:13:05.482Z"}],"details":{"listingId":"53f9f455-4d57-499e-8da6-cbfddedfaa59","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"whisper-cpp-realtime-transcription-pipeline","github":{"repo":"agentskillexchange/skills","stars":8,"topics":["agent-skills","ai-agents","ai-tools","awesome-list","claude-code","codex","cursor","llm","mcp","npx-skills","openclaw","skills-catalog"],"license":"mit","html_url":"https://github.com/agentskillexchange/skills","pushed_at":"2026-05-18T19:02:17Z","description":"The open catalog of AI agent skills — 2,000+ security-scanned skills for Claude Code, Cursor, Codex, and more.","skill_md_sha":"30ac3b40c23fd1c0aeb93f8f1f49470589626201","skill_md_path":"skills/whisper-cpp-realtime-transcription-pipeline/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/whisper-cpp-realtime-transcription-pipeline"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"Whisper.cpp Real-Time Transcription Pipeline","description":"Streams audio from PulseAudio or ALSA devices into whisper.cpp for real-time speech-to-text with word-level timestamps. Outputs SRT/VTT subtitles and JSON transcripts simultaneously."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/whisper-cpp-realtime-transcription-pipeline"},"updatedAt":"2026-05-18T19:13:05.482Z"}}