{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"tool_hedy","slug":"hedy","name":"Hedy","type":"product","url":"https://www.hedy.bot","page_url":"https://unfragile.ai/hedy","categories":["chatbots-assistants"],"tags":[],"pricing":{"model":"freemium","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"tool_hedy__cap_0","uri":"capability://data.processing.analysis.real.time.speech.to.text.transcription.with.speaker.diarization","name":"real-time speech-to-text transcription with speaker diarization","description":"Captures live audio streams from video conference platforms (Zoom, Teams, Google Meet) and converts speech to text in real-time using cloud-based ASR (automatic speech recognition) with speaker identification. The system maintains a rolling buffer of audio chunks, processes them through a speech recognition API, and tags utterances with speaker identities by analyzing audio characteristics and meeting participant metadata. Transcription is streamed to the UI as it completes, enabling live note-taking without post-call processing delays.","intents":["I need a live transcript of my meeting that updates as people speak, not after the call ends","I want to know who said what during the meeting without manually reviewing the recording","I need to capture exact quotes from speakers in real-time for compliance or documentation"],"best_for":["Small teams conducting 1-10 meetings per week who need basic documentation","Solopreneurs and freelancers avoiding manual note-taking overhead","Non-technical users who need plug-and-play setup without API configuration"],"limitations":["Speaker diarization accuracy degrades with >6 simultaneous speakers or heavy accents outside training data","Technical terminology (medical, legal, engineering jargon) has higher error rates than general conversation","Real-time latency typically 2-5 seconds behind actual speech due to ASR processing windows","No support for non-English languages or code-switching between languages"],"requires":["Active video conference account (Zoom, Microsoft Teams, Google Meet, or WebRTC-compatible platform)","Stable internet connection with minimum 2 Mbps upload bandwidth","Browser with WebRTC support (Chrome 60+, Firefox 55+, Safari 11+, Edge 79+)","Microphone and speaker permissions granted to Hedy application"],"input_types":["audio stream (PCM, opus, or platform-native codec)","meeting participant metadata (names, email addresses from calendar integration)"],"output_types":["structured transcript (JSON with timestamps, speaker labels, confidence scores)","plain text transcript (for export/sharing)","speaker turn segments (for timeline navigation)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_1","uri":"capability://text.generation.language.automatic.meeting.summary.generation.with.decision.extraction","name":"automatic meeting summary generation with decision extraction","description":"Processes completed transcripts through a multi-stage NLP pipeline: first, a summarization model (likely fine-tuned T5 or BART) condenses the full transcript into 2-3 paragraph executive summary; second, a named entity recognition (NER) + dependency parsing layer identifies action items, decisions, and owners by detecting imperative verb phrases and linking them to speaker identities; third, a topic segmentation model breaks the meeting into logical sections (agenda items, discussions, decisions). The system uses extractive + abstractive hybrid summarization to preserve exact quotes while generating coherent prose.","intents":["I need a 2-minute summary of a 60-minute meeting to brief someone who couldn't attend","I want to automatically extract who owns which action items without manually reviewing the transcript","I need to identify all decisions made in the meeting and who made them for compliance records"],"best_for":["Product managers and engineering leads running multiple daily standups/planning meetings","Sales teams needing quick deal status summaries from customer calls","HR and legal teams requiring decision audit trails from meetings"],"limitations":["Summary quality degrades on highly technical or domain-specific discussions (medical, legal, financial) where context is critical","Action item extraction misses implicit commitments (e.g., 'we should probably look into that' vs explicit 'I will investigate X by Friday')","No support for multi-language meetings or code-switching; summarization trained on English-only corpora","Summaries are generic and lack customization for industry-specific terminology or decision frameworks","Cannot distinguish between hypothetical discussions and actual decisions without explicit markers"],"requires":["Completed transcript with speaker labels and timestamps","Minimum 5 minutes of meeting content (summaries on <2 min meetings are often incoherent)","English language transcript (non-English requires manual translation or separate model)"],"input_types":["structured transcript (JSON with speaker, timestamp, text fields)","raw text transcript (with or without speaker labels)"],"output_types":["executive summary (2-3 paragraphs of prose)","action items list (structured JSON with owner, task, deadline if mentioned)","decision log (list of decisions with context and decision-maker)","topic outline (hierarchical breakdown of meeting sections)"],"categories":["text-generation-language","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_2","uri":"capability://search.retrieval.meeting.search.and.retrieval.across.historical.transcripts","name":"meeting search and retrieval across historical transcripts","description":"Indexes all meeting transcripts using full-text search (likely Elasticsearch or similar) combined with semantic search via embedding vectors (sentence transformers or OpenAI embeddings). When a user searches, the system performs hybrid retrieval: keyword matching for exact phrase queries (e.g., 'budget approved $50k') and semantic similarity for conceptual queries (e.g., 'what did we decide about pricing?'). Results are ranked by relevance and returned with context snippets showing the speaker, timestamp, and surrounding dialogue. Supports filtering by date range, attendees, and meeting type.","intents":["I need to find what was decided about feature X in a meeting from 3 weeks ago","I want to search across all my meetings for mentions of a specific client or project","I need to retrieve the exact quote from a decision to include in a document or email"],"best_for":["Teams with 50+ meetings per month who need to reference historical decisions","Compliance-heavy industries (finance, healthcare, legal) requiring audit trails of decisions","Product and engineering teams tracking feature requests and decisions across multiple meetings"],"limitations":["Semantic search quality depends on embedding model quality; out-of-domain terminology may not retrieve relevant results","Full-text search is case-insensitive and doesn't handle typos or phonetic variations well","Search latency increases with corpus size; searching across 1000+ meetings may take 2-5 seconds","No support for cross-language search (e.g., searching English query against Spanish meetings)","Indexing lag: newly completed meetings may not be searchable for 30-60 seconds after transcription completes"],"requires":["Minimum 5 historical meetings indexed (search on <5 meetings is not useful)","Search query in English language","Stable internet connection for API calls to search backend"],"input_types":["text search query (natural language or keyword-based)","filter parameters (date range, attendee names, meeting type)"],"output_types":["ranked list of matching transcript segments (JSON with speaker, timestamp, snippet text)","metadata (meeting date, attendees, full transcript link)","context window (surrounding dialogue before/after match)"],"categories":["search-retrieval","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_3","uri":"capability://automation.workflow.meeting.recording.storage.and.playback.with.transcript.synchronization","name":"meeting recording storage and playback with transcript synchronization","description":"Stores meeting recordings (audio or video) in cloud object storage (likely AWS S3 or similar) with automatic transcoding to multiple bitrates for adaptive streaming. The playback interface synchronizes the transcript timeline with video/audio playback: clicking a transcript line seeks the recording to that timestamp, and the current playback position highlights the corresponding transcript line in real-time. Supports variable playback speed (0.5x to 2x) and speaker filtering (hide/show specific speakers' audio). Recordings are encrypted at rest and access-controlled via user permissions.","intents":["I want to review a specific part of the meeting by clicking on the transcript and jumping to that moment in the recording","I need to share a meeting recording with a colleague but only allow them to view it, not download it","I want to listen to just one speaker's contributions without hearing the full meeting"],"best_for":["Teams needing to review complex technical discussions or customer calls in detail","Training and onboarding teams using meetings as reference material","Legal and compliance teams requiring immutable audit trails of meetings"],"limitations":["Storage costs scale linearly with meeting duration and video quality; 1 hour of 1080p video ≈ 2-3 GB","Playback latency on poor connections (< 2 Mbps) may cause buffering or quality degradation","Speaker filtering requires separate audio tracks per speaker (not available if recording captures mixed audio only)","Transcript-video sync can drift if transcription is corrected after recording is uploaded","No built-in video editing or clip extraction; requires external tools to create highlights"],"requires":["Meeting recording in MP3, MP4, or WebM format","Minimum 100 MB free storage per meeting hour (varies by quality)","Browser with HTML5 video support (all modern browsers)","Stable internet connection with minimum 1 Mbps for streaming playback"],"input_types":["audio file (MP3, WAV, AAC)","video file (MP4, WebM, MOV)","transcript with timestamps (JSON or plain text)"],"output_types":["streaming video/audio playback (adaptive bitrate)","synchronized transcript with playback position","shareable recording link with access controls"],"categories":["automation-workflow","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_4","uri":"capability://tool.use.integration.calendar.integration.and.automatic.meeting.capture","name":"calendar integration and automatic meeting capture","description":"Integrates with calendar systems (Google Calendar, Outlook, Zoom, Teams) via OAuth 2.0 to detect scheduled meetings and automatically join video calls. When a meeting starts, Hedy's bot joins the call (as a participant or via platform API), captures audio, and begins transcription without requiring manual user action. The system extracts meeting metadata (title, attendees, duration) from calendar events and associates it with the transcript. Supports recurring meetings and handles timezone conversions for global teams.","intents":["I want Hedy to automatically join and record all my scheduled meetings without me having to manually start it each time","I need meeting metadata (attendees, agenda from calendar) to be automatically attached to transcripts for context","I want to exclude certain meetings (1-on-1s, personal calls) from being recorded based on calendar labels or attendee lists"],"best_for":["Teams with 5+ scheduled meetings per week who want zero-friction capture","Distributed teams across multiple time zones needing automatic documentation","Organizations with strict meeting documentation policies (compliance, audit requirements)"],"limitations":["Calendar integration requires OAuth permissions; some organizations restrict third-party calendar access via admin policies","Bot cannot join meetings on platforms that don't support API-based participant joining (some enterprise Zoom/Teams configurations)","Recurring meeting detection may fail if calendar events are modified or rescheduled frequently","No support for ad-hoc meetings (calls not on calendar); requires manual start for unscheduled calls","Calendar metadata extraction is limited to title, attendees, and time; custom fields or agenda notes are not captured"],"requires":["Active calendar account (Google Calendar, Outlook, or platform-native calendar)","OAuth 2.0 permission grant for calendar read access","Meeting platform account (Zoom, Teams, Google Meet) with API access enabled","Admin approval in enterprise environments for bot participation in calls"],"input_types":["calendar event metadata (title, attendees, start time, duration)","calendar labels or categories (for filtering)"],"output_types":["automatic meeting capture trigger","enriched transcript with calendar metadata","meeting exclusion rules (meetings not to record)"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_5","uri":"capability://data.processing.analysis.meeting.insights.and.analytics.dashboard","name":"meeting insights and analytics dashboard","description":"Aggregates data across all meetings to generate analytics: meeting frequency trends, average meeting duration, attendee participation rates, decision velocity (time from discussion to decision), and topic frequency analysis. The dashboard uses time-series visualization (line charts for trends), heatmaps for attendee participation patterns, and word clouds for common topics. Data is computed via batch jobs (daily or weekly aggregation) rather than real-time, and results are cached for fast dashboard load times. Supports filtering by date range, attendee, and meeting type.","intents":["I want to understand if my team is spending too much time in meetings and identify trends over time","I need to see which team members are most active in meetings and who might be disengaged","I want to identify the most frequently discussed topics to understand team priorities"],"best_for":["Engineering and product managers optimizing team communication patterns","HR and organizational development teams analyzing meeting culture","Executive teams tracking decision velocity and meeting efficiency"],"limitations":["Analytics are computed on batch schedules (daily/weekly), not real-time; insights lag by up to 24 hours","Participation metrics are based on transcript activity (speaking time), not engagement quality; silent observers appear disengaged","Topic analysis is superficial (word frequency) and doesn't understand context; 'budget' appears equally whether discussing budget cuts or budget increases","No support for cross-organization analytics; data is siloed per workspace","Trend analysis requires minimum 20-30 meetings to be statistically meaningful; small teams see noisy data"],"requires":["Minimum 10 historical meetings indexed","Transcripts with speaker labels and timestamps","Stable internet connection for dashboard loading"],"input_types":["aggregated transcript data (speaker, duration, topic)","meeting metadata (date, attendees, duration)"],"output_types":["time-series charts (meeting frequency, duration trends)","participation heatmaps (attendee activity by time/meeting)","topic frequency analysis (word clouds, topic lists)","summary metrics (average meeting duration, decision velocity)"],"categories":["data-processing-analysis","planning-reasoning"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_6","uri":"capability://text.generation.language.transcript.editing.and.correction.with.version.control","name":"transcript editing and correction with version control","description":"Provides a web-based editor for users to manually correct transcription errors (typos, misheard words, speaker labels) after the meeting. Changes are tracked with version history: each edit creates a new version with timestamp and user attribution, allowing rollback to previous versions. The editor uses a diff-based approach to highlight changes between versions. Corrections can be applied to individual words, phrases, or entire speaker turns. The system supports bulk find-and-replace for common errors (e.g., correcting a company name misspelled throughout the transcript).","intents":["I need to fix transcription errors (e.g., 'Kubernetes' transcribed as 'Cubernetes') before sharing the transcript","I want to correct speaker labels where the AI misidentified who was speaking","I need to track who made edits to the transcript and when, for compliance or audit purposes"],"best_for":["Teams with technical or specialized terminology requiring manual correction","Legal and compliance teams needing immutable audit trails of transcript changes","Organizations with strict documentation standards requiring human review before archival"],"limitations":["Manual editing is time-consuming; correcting a 60-minute meeting transcript may take 15-30 minutes","No AI-assisted correction suggestions; users must manually identify and fix errors","Version history storage scales with number of edits; heavily edited transcripts consume more storage","Bulk find-and-replace can introduce errors if applied too broadly (e.g., replacing 'Java' might also replace 'JavaScript')","No collaborative editing; only one user can edit a transcript at a time (no real-time co-editing)"],"requires":["Completed transcript with speaker labels","Write permissions on the meeting/transcript","Web browser with text editing support"],"input_types":["transcript text (plain text or structured JSON)","edit operations (word replacement, speaker label correction, phrase deletion)"],"output_types":["corrected transcript (plain text or JSON)","version history (list of edits with timestamps and user attribution)","diff view (highlighting changes between versions)"],"categories":["text-generation-language","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_7","uri":"capability://data.processing.analysis.meeting.transcript.export.and.format.conversion","name":"meeting transcript export and format conversion","description":"Exports transcripts in multiple formats: plain text (.txt), Microsoft Word (.docx), PDF, JSON (structured with speaker labels and timestamps), SRT (subtitle format for video sync), and CSV (for spreadsheet analysis). The export pipeline handles format-specific requirements: PDF includes formatting and page breaks, Word documents preserve speaker labels and timestamps in a table, JSON maintains full metadata, and SRT generates subtitle timing for video players. Users can customize export options (include/exclude timestamps, speaker labels, summary, action items) before generation.","intents":["I need to export the transcript as a Word document to share with team members who don't have Hedy access","I want to export the transcript as SRT subtitles to sync with the video recording in my video editor","I need to export meeting data as CSV to analyze in Excel or import into another system"],"best_for":["Teams sharing transcripts with external stakeholders (clients, partners, regulators)","Content creators and video editors needing subtitle files for video production","Data analysts and researchers exporting meeting data for analysis in external tools"],"limitations":["PDF export may lose formatting if transcript contains special characters or non-ASCII text","SRT export requires precise timestamp alignment; drift in transcription timing can cause subtitle sync issues","CSV export flattens hierarchical data (e.g., action items with sub-tasks); complex structures may not export cleanly","Large transcripts (>100,000 words) may take 10-30 seconds to export due to format conversion overhead","No support for custom export templates; formatting is fixed per format type"],"requires":["Completed transcript with speaker labels and timestamps","Read permissions on the transcript","Stable internet connection for file download"],"input_types":["transcript data (structured JSON or plain text)","export format selection (txt, docx, pdf, json, srt, csv)","export options (include timestamps, speaker labels, summary, action items)"],"output_types":["exported file in selected format (.txt, .docx, .pdf, .json, .srt, .csv)","downloadable file link (temporary, expires after 24-48 hours)"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"tool_hedy__cap_8","uri":"capability://safety.moderation.meeting.access.control.and.sharing.with.granular.permissions","name":"meeting access control and sharing with granular permissions","description":"Implements role-based access control (RBAC) for meetings and transcripts: Owner (full access), Editor (can edit transcript and share), Viewer (read-only access), and Commenter (can view and add comments). Sharing is done via shareable links with optional password protection and expiration dates (e.g., link expires after 7 days). Access logs track who viewed the transcript and when. Supports team-level permissions (all team members can access team meetings) and individual-level permissions (specific users granted access). Integrates with SSO (single sign-on) for enterprise authentication.","intents":["I need to share a meeting transcript with a client but only allow them to view it, not edit or download it","I want to grant my team access to all meetings automatically without manually sharing each one","I need to revoke access to a meeting transcript after a certain date (e.g., contract ends)"],"best_for":["Enterprise teams with strict data governance and compliance requirements","Consulting and professional services firms sharing client meeting records","Organizations with external stakeholders (clients, partners, vendors) needing selective access"],"limitations":["Shareable links are not revocable once shared; if a link is leaked, anyone with the link can access the meeting until expiration","No support for conditional access (e.g., access only from specific IP addresses or during business hours)","Access logs are stored for audit purposes but not real-time; log queries may take 5-10 seconds","SSO integration requires enterprise plan; not available on free/freemium tiers","No support for fine-grained permissions (e.g., hide specific speakers or redact sensitive information)"],"requires":["User account with owner or editor role on the meeting","Recipient email address or shareable link generation","SSO integration (for enterprise authentication) requires IT admin setup"],"input_types":["permission role (owner, editor, viewer, commenter)","recipient email or shareable link generation","expiration date (optional)","password protection (optional)"],"output_types":["shareable link with access token","access log (user, timestamp, action)","permission list (users and roles)"],"categories":["safety-moderation","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":39,"verified":false,"data_access_risk":"high","permissions":["Active video conference account (Zoom, Microsoft Teams, Google Meet, or WebRTC-compatible platform)","Stable internet connection with minimum 2 Mbps upload bandwidth","Browser with WebRTC support (Chrome 60+, Firefox 55+, Safari 11+, Edge 79+)","Microphone and speaker permissions granted to Hedy application","Completed transcript with speaker labels and timestamps","Minimum 5 minutes of meeting content (summaries on <2 min meetings are often incoherent)","English language transcript (non-English requires manual translation or separate model)","Minimum 5 historical meetings indexed (search on <5 meetings is not useful)","Search query in English language","Stable internet connection for API calls to search backend"],"failure_modes":["Speaker diarization accuracy degrades with >6 simultaneous speakers or heavy accents outside training data","Technical terminology (medical, legal, engineering jargon) has higher error rates than general conversation","Real-time latency typically 2-5 seconds behind actual speech due to ASR processing windows","No support for non-English languages or code-switching between languages","Summary quality degrades on highly technical or domain-specific discussions (medical, legal, financial) where context is critical","Action item extraction misses implicit commitments (e.g., 'we should probably look into that' vs explicit 'I will investigate X by Friday')","No support for multi-language meetings or code-switching; summarization trained on English-only corpora","Summaries are generic and lack customization for industry-specific terminology or decision frameworks","Cannot distinguish between hypothetical discussions and actual decisions without explicit markers","Semantic search quality depends on embedding model quality; out-of-domain terminology may not retrieve relevant results","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.31666666666666665,"quality":0.67,"ecosystem":0.15000000000000002,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:30.893Z","last_scraped_at":"2026-04-05T13:23:42.560Z","last_commit":null},"community":{"stars":null,"forks":null,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=hedy","compare_url":"https://unfragile.ai/compare?artifact=hedy"}},"signature":"1X8hAevgvvivWPw6pbJ30jM5WUmjzmWGEmJPm9irprjN9UsV3/ezjvwwafpIAnUvbMsfWdULQCe1kffT2GUDAg==","signedAt":"2026-06-22T04:05:47.397Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/hedy","artifact":"https://unfragile.ai/hedy","verify":"https://unfragile.ai/api/v1/verify?slug=hedy","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}