[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"workflow-asset-15ab68d2":3,"seo:featured-workflow:15ab68d2-4ddc-11f1-9bc6-00163e2b0d79:fr":83,"workflow-related-asset-15ab68d2-15ab68d2-4ddc-11f1-9bc6-00163e2b0d79":84},{"id":4,"uuid":5,"slug":6,"title":7,"description":8,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":12,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":14,"tags":21,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":28,"asset_kind":29,"target_tools":30,"install_mode":34,"entrypoint":18,"risk_profile":35,"dependencies":37,"verification":43,"agent_metadata":46,"agent_fit":59,"trust":71,"provenance":80,"created_at":82,"updated_at":82},3243,"15ab68d2-4ddc-11f1-9bc6-00163e2b0d79","asset-15ab68d2","Vosk — Offline Speech Recognition API for Any Platform","Vosk provides offline speech recognition for Android, iOS, Raspberry Pi, and servers with support for 20+ languages, all without an internet connection.","8a910e34-3180-11f1-9bc6-00163e2b0d79","Script Depot","",0,"en",[15],{"id":16,"step_order":17,"title":18,"description":11,"prompt_template":19,"variables":11,"depends_on":20,"expected_output":11},3806,1,"Vosk Speech Recognition","# Vosk — Offline Speech Recognition API for Any Platform\n\n## Quick Use\n```bash\npip install vosk\npython -c \"\nfrom vosk import Model, KaldiRecognizer\nimport wave\nmodel = Model(model_name='vosk-model-small-en-us-0.15')\nwf = wave.open('test.wav', 'rb')\nrec = KaldiRecognizer(model, wf.getframerate())\nwhile True:\n    data = wf.readframes(4000)\n    if len(data) == 0:\n        break\n    rec.AcceptWaveform(data)\nprint(rec.FinalResult())\n\"\n```\n\n## Introduction\nVosk is an offline speech recognition toolkit that runs entirely on-device without sending audio to the cloud. It wraps the Kaldi ASR engine into a developer-friendly API available in Python, Java, C#, Node.js, and more, enabling low-latency transcription on everything from a Raspberry Pi to a production server.\n\n## What Vosk Does\n- Transcribes audio to text in 20+ languages without internet\n- Provides real-time streaming recognition with partial results\n- Supports speaker identification alongside transcription\n- Runs on ARM devices including Raspberry Pi and Android\n- Offers lightweight models as small as 50 MB for embedded use\n\n## Architecture Overview\nVosk uses Kaldi's finite-state transducer decoding pipeline compiled into a shared library. Language and acoustic models are bundled into downloadable packages. The KaldiRecognizer class processes audio frames incrementally and emits JSON results with transcribed text, confidence scores, and word-level timestamps.\n\n## Self-Hosting & Configuration\n- Install via pip, npm, NuGet, or Maven depending on your stack\n- Download a pre-trained model from the Vosk model repository\n- Point the Model constructor to the extracted model directory\n- Set sample rate to match your audio source (typically 16000 Hz)\n- Deploy vosk-server for WebSocket-based real-time transcription\n\n## Key Features\n- Fully offline operation with no cloud dependency\n- Small-footprint models for constrained hardware (50-300 MB)\n- Word-level timestamps and confidence scores in JSON output\n- Speaker diarization to identify who is speaking\n- WebSocket server mode for scalable deployments\n\n## Comparison with Similar Tools\n- **Whisper** — higher accuracy but requires more compute; Vosk excels on edge devices\n- **DeepSpeech** — discontinued; Vosk is actively maintained with broader language support\n- **Google Speech-to-Text** — cloud-only and paid; Vosk runs offline and free\n- **whisper.cpp** — efficient Whisper port but lacks Vosk's streaming partial-result API\n\n## FAQ\n**Q: Does Vosk require a GPU?**\nA: No. Vosk runs on CPU and is optimized for low-power devices.\n\n**Q: What audio formats does Vosk accept?**\nA: Raw PCM audio (mono, 16-bit). Use ffmpeg to convert other formats.\n\n**Q: Can I train a custom model?**\nA: Yes. Vosk models are standard Kaldi models that can be trained with the Kaldi toolkit.\n\n**Q: How does streaming work?**\nA: Call AcceptWaveform in a loop with audio chunks; partial results arrive immediately.\n\n## Sources\n- https:\u002F\u002Fgithub.com\u002Falphacep\u002Fvosk-api\n- https:\u002F\u002Falphacephei.com\u002Fvosk\u002F","0",[22],{"id":23,"name":24,"slug":25,"icon":26},11,"Scripts","script","📜",false,"3a0cf109cfcd3b89e7e226c0f657952d128ba3a2bb46be6e068b000ff8504543","skill",[31,32,33],"claude_code","codex","gemini_cli","single",{"executes_code":27,"modifies_global_config":27,"requires_secrets":36,"uses_absolute_paths":27,"network_access":27},[],{"npm":38,"pip":39,"brew":41,"system":42},[],[40],"vosk",[],[],{"commands":44,"expected_files":45},[],[18],{"asset_kind":29,"target_tools":47,"install_mode":34,"entrypoint":18,"risk_profile":48,"dependencies":50,"content_hash":28,"verification":55,"inferred":58},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":49,"uses_absolute_paths":27,"network_access":27},[],{"npm":51,"pip":52,"brew":53,"system":54},[],[40],[],[],{"commands":56,"expected_files":57},[],[18],true,{"target":32,"score":60,"status":61,"policy":62,"why":63,"asset_kind":29,"install_mode":34},98,"native","allow",[64,65,66,67,68,69,70],"target_tools includes codex","asset_kind skill","install_mode single","markdown-only","policy allow","safe markdown-only Codex install","trust established",{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":28,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":74,"review_status":75,"signals":76},"established","hash_only",[],"unreviewed",[77,78,79],"author has published assets","content hash available","no dangerous capability badges",{"owner_uuid":9,"owner_name":10,"source_url":81,"content_hash":28,"visibility":17,"created_at":82,"updated_at":82},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-15ab68d2","2026-05-12 16:25:07",null,[85,141,188,234],{"id":86,"uuid":87,"slug":88,"title":89,"description":90,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":91,"time_saved":12,"model_used":92,"fork_count":12,"vote_count":12,"view_count":93,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":94,"tags":95,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":97,"asset_kind":29,"target_tools":98,"install_mode":34,"entrypoint":89,"risk_profile":101,"dependencies":103,"verification":108,"agent_metadata":111,"agent_fit":123,"trust":125,"provenance":129,"created_at":131,"updated_at":132,"__relatedScore":133,"__relatedReasons":134,"__sharedTags":139},287,"c43ad870-8c99-471a-898e-b07140faf532","whisperx-70x-faster-speech-recognition-c43ad870","WhisperX — 70x Faster Speech Recognition","WhisperX provides 70x realtime speech recognition with word-level timestamps and speaker diarization. 21K+ GitHub stars. Batched inference, under 8GB VRAM. BSD-2-Clause.",500,"Claude Code",184,[],[96],{"id":23,"name":24,"slug":25,"icon":26},"f7d6b8fdaefb5379db3d5dfc6ac3cea025c073b66e63fbfa8184310a4928146b",[31,32,99,33,100],"cursor","windsurf",{"executes_code":27,"modifies_global_config":27,"requires_secrets":102,"uses_absolute_paths":27,"network_access":27},[],{"npm":104,"pip":105,"brew":106,"system":107},[],[],[],[],{"commands":109,"expected_files":110},[],[89],{"asset_kind":29,"target_tools":112,"install_mode":34,"entrypoint":89,"risk_profile":113,"dependencies":115,"content_hash":97,"verification":120},[31,32,99,33,100],{"executes_code":27,"modifies_global_config":27,"requires_secrets":114,"uses_absolute_paths":27,"network_access":27},[],{"npm":116,"pip":117,"brew":118,"system":119},[],[],[],[],{"commands":121,"expected_files":122},[],[89],{"target":32,"score":60,"status":61,"policy":62,"why":124,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":97,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":126,"review_status":75,"signals":127},[],[128,77,78,79],"asset has usage views",{"owner_uuid":9,"owner_name":10,"source_url":130,"content_hash":97,"visibility":17,"created_at":131,"updated_at":132},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fwhisperx-70x-faster-speech-recognition-c43ad870","2026-04-01 06:14:01","2026-05-12 04:39:07",106.40075759260452,[135,136,137,138],"topic-match","same-kind","same-target","same-author",[25,140],"scripts",{"id":142,"uuid":143,"slug":144,"title":145,"description":146,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":147,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":148,"tags":149,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":151,"asset_kind":29,"target_tools":152,"install_mode":34,"entrypoint":153,"risk_profile":154,"dependencies":156,"verification":161,"agent_metadata":164,"agent_fit":176,"trust":178,"provenance":181,"created_at":183,"updated_at":184,"__relatedScore":185,"__relatedReasons":186,"__sharedTags":187},3073,"dd235d25-4d54-11f1-9bc6-00163e2b0d79","asset-dd235d25","draw.io — Free Open-Source Diagramming Tool for Any Platform","draw.io is a free, browser-based diagramming application that supports flowcharts, UML, network diagrams, and more. Works offline as a desktop app on Windows, macOS, and Linux with no account required.",27,[],[150],{"id":23,"name":24,"slug":25,"icon":26},"e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",[31,32,33],"SKILL.md",{"executes_code":27,"modifies_global_config":27,"requires_secrets":155,"uses_absolute_paths":27,"network_access":27},[],{"npm":157,"pip":158,"brew":159,"system":160},[],[],[],[],{"commands":162,"expected_files":163},[],[],{"asset_kind":29,"target_tools":165,"install_mode":34,"entrypoint":153,"risk_profile":166,"dependencies":168,"content_hash":151,"verification":173,"inferred":58},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":167,"uses_absolute_paths":27,"network_access":27},[],{"npm":169,"pip":170,"brew":171,"system":172},[],[],[],[],{"commands":174,"expected_files":175},[],[],{"target":32,"score":60,"status":61,"policy":62,"why":177,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":151,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":179,"review_status":75,"signals":180},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":182,"content_hash":151,"visibility":17,"created_at":183,"updated_at":184},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-dd235d25","2026-05-12 00:17:10","2026-05-12 18:45:25",99.17073704701333,[135,136,137,138],[25,140],{"id":189,"uuid":190,"slug":191,"title":192,"description":193,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":194,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":195,"tags":196,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":198,"asset_kind":29,"target_tools":199,"install_mode":34,"entrypoint":153,"risk_profile":200,"dependencies":202,"verification":207,"agent_metadata":210,"agent_fit":222,"trust":224,"provenance":227,"created_at":229,"updated_at":230,"__relatedScore":231,"__relatedReasons":232,"__sharedTags":233},1193,"409089e0-372b-11f1-9bc6-00163e2b0d79","keepassxc-cross-platform-offline-password-manager-409089e0","KeePassXC — Cross-Platform Offline Password Manager","KeePassXC is a free, open-source, cross-platform password manager that keeps your passwords in an encrypted local database. No cloud sync, no subscription, no telemetry — just a secure, audited vault protected by a master password and optional key file.",73,[],[197],{"id":23,"name":24,"slug":25,"icon":26},"81b6e80b4d77ab131c91ddf306516de80939bb28a90422b676e372c6d8c324ac",[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":201,"uses_absolute_paths":27,"network_access":27},[],{"npm":203,"pip":204,"brew":205,"system":206},[],[],[],[],{"commands":208,"expected_files":209},[],[11],{"asset_kind":29,"target_tools":211,"install_mode":34,"entrypoint":153,"risk_profile":212,"dependencies":214,"content_hash":198,"verification":219},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":213,"uses_absolute_paths":27,"network_access":27},[],{"npm":215,"pip":216,"brew":217,"system":218},[],[],[],[],{"commands":220,"expected_files":221},[],[11],{"target":32,"score":60,"status":61,"policy":62,"why":223,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":198,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":225,"review_status":75,"signals":226},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":228,"content_hash":198,"visibility":17,"created_at":229,"updated_at":230},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fkeepassxc-cross-platform-offline-password-manager-409089e0","2026-04-13 19:23:53","2026-05-12 19:25:53",96.80384757959646,[135,136,137,138],[25,140],{"id":235,"uuid":236,"slug":237,"title":238,"description":239,"author_id":9,"author_name":10,"author_avatar":11,"token_estimate":12,"time_saved":12,"model_used":11,"fork_count":12,"vote_count":12,"view_count":240,"parent_id":12,"parent_uuid":11,"lang_type":13,"steps":241,"tags":242,"has_voted":27,"visibility":17,"share_token":11,"is_featured":12,"content_hash":151,"asset_kind":29,"target_tools":244,"install_mode":34,"entrypoint":153,"risk_profile":245,"dependencies":247,"verification":252,"agent_metadata":255,"agent_fit":267,"trust":269,"provenance":272,"created_at":274,"updated_at":275,"__relatedScore":276,"__relatedReasons":277,"__sharedTags":278},2929,"8756aaa0-4c49-11f1-9bc6-00163e2b0d79","asset-8756aaa0","SpeechBrain — Open-Source All-in-One Speech and Audio Processing Toolkit","SpeechBrain is a PyTorch-based toolkit covering speech recognition, speaker verification, text-to-speech, speech separation, language modeling, and spoken language understanding in a single framework.",19,[],[243],{"id":23,"name":24,"slug":25,"icon":26},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":246,"uses_absolute_paths":27,"network_access":27},[],{"npm":248,"pip":249,"brew":250,"system":251},[],[],[],[],{"commands":253,"expected_files":254},[],[],{"asset_kind":29,"target_tools":256,"install_mode":34,"entrypoint":153,"risk_profile":257,"dependencies":259,"content_hash":151,"verification":264,"inferred":58},[31,32,33],{"executes_code":27,"modifies_global_config":27,"requires_secrets":258,"uses_absolute_paths":27,"network_access":27},[],{"npm":260,"pip":261,"brew":262,"system":263},[],[],[],[],{"commands":265,"expected_files":266},[],[],{"target":32,"score":60,"status":61,"policy":62,"why":268,"asset_kind":29,"install_mode":34},[64,65,66,67,68,69,70],{"author_trust_level":72,"verified_publisher":27,"asset_signed_hash":151,"signature_status":73,"install_count":12,"report_count":12,"dangerous_capability_badges":270,"review_status":75,"signals":271},[],[77,78,79],{"owner_uuid":9,"owner_name":10,"source_url":273,"content_hash":151,"visibility":17,"created_at":274,"updated_at":275},"https:\u002F\u002Ftokrepo.com\u002Fen\u002Fworkflows\u002Fasset-8756aaa0","2026-05-10 16:23:31","2026-05-12 18:00:32",93.95154499349597,[135,136,137,138],[25,140]]