{"id":"4547f52e-fbcf-4820-b15f-1477bcb5de46","shortId":"wdBvNp","kind":"skill","title":"faster-whisper High-Performance Speech Transcription Engine","tagline":"faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2 that delivers up to 4x faster transcription with lower memory usage. It supports CPU and GPU inference with 8-bit quantization, batch processing, word-level timestamps, and VAD filtering for accurate","description":"# faster-whisper High-Performance Speech Transcription Engine\n\nfaster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2 that delivers up to 4x faster transcription with lower memory usage. It supports CPU and GPU inference with 8-bit quantization, batch processing, word-level timestamps, and VAD filtering for accurate speech-to-text conversion.\n\n## Installation\n\nUse the upstream install or setup path that matches your environment:\n- #### Use Docker\n- pip install nvidia-cublas-cu12 nvidia-cudnn-cu12==9.*\n- pip install faster-whisper\n- pip install --force-reinstall \"faster-whisper @ https://github.com/SYSTRAN/faster-whisper/archive/refs/heads/master.tar.gz\"\n\nRequirements and caveats from upstream:\n- Python 3.9 or greater\n- Unlike openai-whisper, FFmpeg does **not** need to be installed on the system. The audio is decoded with the Python library [PyAV](https://github.com/PyAV-Org/PyAV) which bundles the FFmpeg libraries in its package.\n- GPU execution requires the following NVIDIA libraries to be installed:\n\nBasic usage or getting-started notes:\n- For reference, here's the time and memory usage that are required to transcribe [**13 minutes**](https://www.youtube.com/watch?v=0u7tTptBo9I) of audio using different implementations:\n- | Implementation | Precision | Beam size | Time | VRAM Usage |\n- | Implementation | Precision | Beam size | Time | RAM Usage |\n\n- Source: https://github.com/SYSTRAN/faster-whisper\n- Extracted from upstream docs: https://raw.githubusercontent.com/SYSTRAN/faster-whisper/HEAD/README.md\n\n## Source\n\n- [Agent Skill Exchange](https://agentskillexchange.com/skills/faster-whisper-high-performance-speech-transcription/)","tags":["faster","whisper","high","performance","speech","transcription","skills","agentskillexchange","agent-skills","ai-agents","ai-tools","awesome-list"],"capabilities":["skill","source-agentskillexchange","skill-faster-whisper-high-performance-speech-transcription","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/faster-whisper-high-performance-speech-transcription","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 (1,684 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":"2026-05-18T19:10:25.748Z","embedding":null,"createdAt":"2026-05-18T13:16:30.508Z","updatedAt":"2026-05-18T19:10:25.748Z","lastSeenAt":"2026-05-18T19:10:25.748Z","tsv":"'/pyav-org/pyav)':189 '/skills/faster-whisper-high-performance-speech-transcription/)':270 '/systran/faster-whisper':256 '/systran/faster-whisper/archive/refs/heads/master.tar.gz':154 '/systran/faster-whisper/head/readme.md':263 '/watch?v=0u7ttptbo9i)':233 '13':229 '3.9':161 '4x':27,81 '8':41,95 '9':138 'accur':54,108 'agent':265 'agentskillexchange.com':269 'agentskillexchange.com/skills/faster-whisper-high-performance-speech-transcription/)':268 'audio':179,235 'basic':208 'batch':44,98 'beam':241,248 'bit':42,96 'bundl':191 'caveat':157 'convers':113 'cpu':36,90 'ctranslate2':22,76 'cu12':133,137 'cubla':132 'cudnn':136 'decod':181 'deliv':24,78 'differ':237 'doc':260 'docker':127 'engin':9,63 'environ':125 'exchang':267 'execut':199 'extract':257 'faster':2,11,28,56,65,82,142,150 'faster-whisp':1,10,55,64,141,149 'ffmpeg':168,193 'filter':52,106 'follow':202 'forc':147 'force-reinstal':146 'get':212 'getting-start':211 'github.com':153,188,255 'github.com/pyav-org/pyav)':187 'github.com/systran/faster-whisper':254 'github.com/systran/faster-whisper/archive/refs/heads/master.tar.gz':152 'gpu':38,92,198 'greater':163 'high':5,59 'high-perform':4,58 'implement':238,239,246 'infer':39,93 'instal':114,118,129,140,145,174,207 'level':48,102 'librari':185,194,204 'lower':31,85 'match':123 'memori':32,86,222 'minut':230 'model':20,74 'need':171 'note':214 'nvidia':131,135,203 'nvidia-cublas-cu12':130 'nvidia-cudnn-cu12':134 'openai':17,71,166 'openai-whisp':165 'packag':197 'path':121 'perform':6,60 'pip':128,139,144 'precis':240,247 'process':45,99 'pyav':186 'python':160,184 'quantiz':43,97 'ram':251 'raw.githubusercontent.com':262 'raw.githubusercontent.com/systran/faster-whisper/head/readme.md':261 'refer':216 'reimplement':15,69 'reinstal':148 'requir':155,200,226 'setup':120 'size':242,249 'skill':266 'skill-faster-whisper-high-performance-speech-transcription' 'sourc':253,264 'source-agentskillexchange' 'speech':7,61,110 'speech-to-text':109 'start':213 'support':35,89 'system':177 'text':112 'time':220,243,250 'timestamp':49,103 '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' 'transcrib':228 'transcript':8,29,62,83 'unlik':164 'upstream':117,159,259 'usag':33,87,209,223,245,252 'use':21,75,115,126,236 'vad':51,105 'vram':244 'whisper':3,12,19,57,66,73,143,151,167 'word':47,101 'word-level':46,100 'www.youtube.com':232 'www.youtube.com/watch?v=0u7ttptbo9i)':231","prices":[{"id":"4ade382d-8101-4918-bfc0-b4674bd0e052","listingId":"4547f52e-fbcf-4820-b15f-1477bcb5de46","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":"2026-05-18T13:16:30.508Z"}],"sources":[{"listingId":"4547f52e-fbcf-4820-b15f-1477bcb5de46","source":"github","sourceId":"agentskillexchange/skills/faster-whisper-high-performance-speech-transcription","sourceUrl":"https://github.com/agentskillexchange/skills/tree/main/skills/faster-whisper-high-performance-speech-transcription","isPrimary":false,"firstSeenAt":"2026-05-18T13:16:30.508Z","lastSeenAt":"2026-05-18T19:10:25.748Z"}],"details":{"listingId":"4547f52e-fbcf-4820-b15f-1477bcb5de46","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"agentskillexchange","slug":"faster-whisper-high-performance-speech-transcription","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":"1b01273ea03f4056a308c8f0605c8619d6243b59","skill_md_path":"skills/faster-whisper-high-performance-speech-transcription/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/agentskillexchange/skills/tree/main/skills/faster-whisper-high-performance-speech-transcription"},"layout":"multi","source":"github","category":"skills","frontmatter":{"name":"faster-whisper High-Performance Speech Transcription Engine","description":"faster-whisper is a reimplementation of OpenAI's Whisper model using CTranslate2 that delivers up to 4x faster transcription with lower memory usage. It supports CPU and GPU inference with 8-bit quantization, batch processing, word-level timestamps, and VAD filtering for accurate speech-to-text conversion."},"skills_sh_url":"https://skills.sh/agentskillexchange/skills/faster-whisper-high-performance-speech-transcription"},"updatedAt":"2026-05-18T19:10:25.748Z"}}