Skip to main content
Glama
811,925 tools. Updated 2026-11-20 17:13

"Transcribing Voice Conversations into Structured Meeting Notes" matching MCP tools:

  • Transcribe English audio AND score how it was said in one call: transcript, tagged transcript, selected scores from 15 emotion and 16 speaking-style labels, and time-local segments. Use this when the user cares about both the words and the delivery — meetings, support calls, interviews, voice notes. Accepts wav/flac/mp3/m4a/ogg/webm. Up to 30 MB via audio_url or 8 MiB decoded via audio_base64; up to 60 minutes of English speech. Returns compact summaries by default. For words only use oruk_transcribe_audio; for tone only use oruk_analyze_tone.
    ConnectorNo auth
  • Turn a script into a finished 1080p video — narrated, cut to matched stock footage, subtitles burned in, audio normalized to −14 LUFS. Returns a job id; poll get_job, then fetch_video. Use when you need a publishable video and have only text. $0.60 per video in USDC on Solana — no account, no API key, no human in the loop. script: narration body to speak (plain text) title: optional intro title shown for ~4s at the top voice: voice id from list_voices(), e.g. female_warm subtitles: burn-in subtitles (default true) speed: narration speed multiplier, e.g. 1.0 seed: stock-selection seed for reproducible visuals, e.g. 7
    ConnectorNo auth
  • Reads a text aloud in a natural Portuguese voice from Fish Audio — Rafael by default, or one of six others — and returns an MP3. WHEN TO USE: the user wants to hear a Portuguese text or needs an audio file of it — narration, audiobook, lesson, voice-over, a message read aloud. The voices speak Portuguese (Brazil, and Tomás from Portugal); a text in another language is read with their accent. HOW IT WORKS: - Up to 50,000 characters per call. A text over 1,000 characters is split by sentence into parts of up to 1,000; the parts are voiced three at a time and joined in order into ONE MP3. Progress is reported per part ("Gerando áudio... 3 de 18"), so keep waiting while it arrives. - It takes time: about 25 seconds per round of three parts. 1,000 characters ≈ 25 s; 5,000 ≈ 1 min; 16,000 ≈ 2.5 min; 50,000 ≈ 7 min. - Over 50,000 characters: split the text at paragraph boundaries into several calls with the same voice and speed, and give the user every link, in order. - Send the text as it should be HEARD: remove Markdown marks (**, #, list bullets), URLs, emojis and tables. Do not summarize, translate or reword unless the user asked — every word you send is read. - voice: rafael (default) or beatriz for clear, neutral narration; tomas for European Portuguese; narrador-propagandas for ads; rodolfo, sao-cipriano and capitao-nascimento are deep character voices. - speed: 1 is the voice's natural pace; 0.9 suits calm narration, 1.2 a quick read. RETURNS: - audioUrl: the complete MP3 to download, valid for 7 days. Always give this link to the user. If you can run commands, you can download it (e.g. curl -o audio.mp3 <audioUrl>). - audio: the MP3 itself, only when it is short (about a minute or less); otherwise null. - seconds (duration), parts, characters, voice, speed. - link: this tool's web page with the same voice and speed (the text is not in it). ERRORS say what happened and what to do next. If a part fails, no audio is produced and a new call starts again from part 1.
    ConnectorNo auth
  • Owners only (needs sign-in): Sets the speech model voice for this business's phone line (inbound and every place_phone_call), until changed again. Default is Aoede. Pass a Gemini prebuilt voice name (letters only, e.g. "Aoede", "Puck"); pass an empty string to reset to the default. place_phone_call cannot pick a different voice per call — set it here or read phone.call_voice in receptionist_service. Tone and language on a specific outbound call belong in place_phone_call's purpose; the inbound opening line belongs in front_desk greeting (update_front_desk).
    ConnectorNo auth
  • List and browse the user's saved notes — their stored knowledge and memories (preferences, workflows, projects, meeting notes, references, and the rest) — with optional filtering, sorting, and pagination. Use search instead when hunting for a topic or keyword; use this to enumerate a folder, tag, or scope. Returns paginated results as a JSON array, followed by a line stating how many notes matched in total and whether more pages remain — read it to know if you have the whole folder before acting on it. Optional: team_id (integer) to list team notes, scope ('active'|'archived'|'inbox'|'favorited'|'trashed'), container_id (integer) with include_nested (boolean), tags (array of strings, AND logic), tag_ids (array of integers, AND logic), summary_stale (boolean, filter to notes with outdated summaries), stale (boolean, filter to notes whose freshness is stale — past their review_after date or unverified for a while), sort ('recent'|'oldest'|'title'), page (integer, default 1), per_page (integer, max 100, default 25), include_body (boolean, default false — include each note's full body, so a scoped/paginated listing can retrieve complete contents without a notes-get call per note; withheld for trashed notes, same as notes-get), include_instructions (boolean, defaults to include_body — include each note's inherited_instructions, the same chain notes-get returns, so a full-body listing also carries the rules governing those notes; withheld for trashed notes). container_id can be combined with team_id to list a specific team container. Example: list ruby-tagged notes in a container: {container_id: 5, tags: ['ruby']}.
    ConnectorOAuth
  • List support-chat conversations in the inbox (open + snoozed by default; pass status='all' to include closed). Read-only; returns the matching conversations, empty when the inbox is clear. Optional product_id to scope to one product; open a full thread with get_conversation.
    ConnectorNo auth

Matching MCP Servers

  • A
    license
    Not graded
    quality
    F
    maintenance
    Enables recording microphone and Mac system audio during meetings, transcribing locally with Parakeet or via Gemini Live, and delivering silence-separated transcript segments to the Claude Code session that started recording.
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Read-only MCP server that exposes locally generated voice notes to any MCP client, allowing listing, searching, and reading transcripts, summaries, and knowledge graphs from voice-notes sessions.
    1
    MIT

Matching MCP Connectors

  • Turn meeting notes or transcripts into a clean structured summary document from chat.

  • Search and read Speechyou voice notes and meeting transcripts from Claude and compatible MCP clients. Retrieve complete transcripts, existing AI summaries, tags, and audio links through four read-only tools. OAuth 2.1 sign-in requires no API key and only accesses notes you own or that were shared with you. Setup: https://speechyou.com/mcp

  • FluxInk document layout generator. Transform raw text content into a structured PDF using one of seven study or work templates, then preview it in an embedded PDF viewer widget. Supported layout_type values. cornell is the Cornell note taking layout with cue, notes, and summary. bullet_points is a clean bulleted summary. zettelkasten is atomic linked notes. journalism_5w1h is who, what, when, where, why, and how. meeting_add is a meeting agenda plus action items. sq3r is Survey, Question, Read, Recite, Review study notes. pso is Problem, Solution, Outcome. Use this when the user asks for a Cornell sheet, bulleted summary, Zettelkasten card, 5W1H breakdown, meeting agenda or minutes, SQ3R study sheet, or PSO writeup. Use this when the user wants to turn raw notes, lecture transcript, or source material into a printable PDF or formatted study sheet. Use this when the user asks for a downloadable PDF document of their content. Do NOT use this when the user just asks for a plain summary in chat. Give it inline. Do NOT use this when the user wants to handwrite or draw something. Call show_handwriting_canvas instead. Do NOT use this when the user wants text in a personal handwriting style. Call show_style_canvas instead. Do NOT use this for plain informational requests with no document generation intent. Always pass the source material verbatim in the content parameter. Do NOT pre summarize. The layout engine handles structuring. Pick the layout_type that best matches the stated purpose. If unclear, ask one short clarifying question instead of guessing. Do NOT re-call if a layout PDF is already visible from a previous turn unless the user explicitly asks for a different layout, different content, or a regeneration. After calling, write a single short acknowledgement and do NOT restate the PDF content.
    ConnectorNo auth
  • Set the voiceover voice for every clip in a project, or only for the clips in `clip_ids`. Use this to apply a clueprint's voice (read `voiceover.voice.name` and `voiceover.voice.engine` from the clueprint source data), or to switch all clips to a specific voice in one call. When the user names specific clips, pass their ids in `clip_ids` so the other clips keep their voice. The voice is looked up by name (case-insensitive; a saved voice's code also works), preferring `voice_engine`. Never guess a name: a name that matches nothing applies the workspace default and returns `matched: false` with a note. Then pick a real voice with find(type='voices'), re-apply, and tell the user. `engine_substituted: true` means the named voice exists only on another engine and was applied there. Common engines: 'eleven' (ElevenLabs), 'cartesia', 'google'. ElevenLabs voices use the latest voice generation unless `voice_version` says otherwise; a voice the workspace saved keeps its saved version. Leave it unset; pass "legacy" ONLY when the user explicitly asks for the legacy/older voice generation.
    ConnectorNo auth
  • List topic rollups for the account website with visibility score, share of voice, ranks, deltas, and per-topic competitors (ranks 1–10). List order is not importance order — sort yourself when ranking opportunities. promptCount is the topic's prompt total and may exceed how many rows list_prompts returns for that topic. Use `list_prompts` when you need per-prompt detail or coverage-gap counts. When no website is set up for the account, returns setup guidance pointing to https://beamtrace.com/setup and an empty structured payload (null period/metrics or empty lists) — follow server instructions; do not invent dates or scores.
    ConnectorOAuth
  • Sets or corrects a lead's category (tag), typically to fix an AI misclassification of a reply. Setting meeting_booked behaves exactly like marking a meeting as booked. Changing the category away from meeting_booked does NOT clear the booked-meeting mark: that mark is removed only by unmarking the meeting. A real change fires the LeadCategoryUpdate webhook; setting the value the lead already has is a no-op.
    ConnectorNo auth
  • Create a new saved character/actor for UGC video — the API equivalent of adding an actor in the dashboard. Supply ONE of: fromLibraryId (clone a preset from list_character_library into the user's saved actors — FREE, name/voice default to the preset's); imageUrl (a public/hosted image — use import_asset_from_url or create_upload first if you only have raw bytes — saved for FREE); or a text prompt to AI-generate a 9:16 portrait (SPENDS 1 credit). Returns characterId to pass as the UGC characterId on create_video. Optionally set defaultVoiceId. NOTE: a library preset can already be used directly as a UGC characterId — only clone it here when the user wants their own editable copy (e.g. a custom voice).
    Connector
    Destructive
    OAuth
  • AI cleanup of a recording: `speech` = noise + room removal (strength subtle/medium/strong), `music` = keep only the voice from a mixed track, `bg_music` = voice + a little of the original bed. Free. Produces a NEW audio_file_id — use it as the voice source in cast_build_project (cuts planned on the original still apply: same timeline). Enhance the ORIGINAL upload, not an already-enhanced file. On the free plan an API call returns a 60-second head preview (enough to A/B it) — the full-length render is one free click in the editor, or a paid-plan API call. The response says which you got.
    ConnectorOAuth
  • Query WhatsApp data: conversations, contacts, messages, transcriptions, labels, and communities. Supports listing, searching, filtering, and looking up by ID. Several WhatsApp accounts may be connected (e.g. personal + business), each with its own conversations, contacts and messages. entity="session" lists the connected accounts and their session IDs; target_session routes a query to one of them. Reading messages: Passing a conversation id (e.g. "5491157390064@c.us") returns the conversation with its messages; limit sets how many. entity="messages" is a global text search across conversations. Audio transcriptions: entity="transcriptions" (with an optional query) returns voice-note transcriptions; messages read by conversation id include the transcription text of audio messages. Examples: List sessions: { entity: "session" } List conversations: {} Target specific account: { entity: "conversations", target_session: "sess_abc123" } Read messages: { id: "5491157390064@c.us" } Read last 100 msgs: { id: "5491157390064@c.us", limit: 100 } Search globally: { query: "meeting" } Search in chat: { id: "5491157390064@c.us", query: "meeting" } Unread conversations: { unread: true } Search contacts: { query: "Alice", entity: "contacts" } List labels: { entity: "labels" } Filter by label: { label: "Important", entity: "conversations" } List communities: { entity: "communities" } Filter by community: { community: "My Community", entity: "conversations" } Find which groups a contact is in: { id: "5491157390064@c.us", entity: "contacts", include_participants: true } List members of a group: { entity: "contacts", group: "120363421729019499@g.us" }
    ConnectorOAuth
  • Create an instant voice clone from a speech recording (ElevenLabs). Only clone the user's own voice or a voice they have permission to use. Best results: 1–2 minutes of clean speech with no music or background noise. Costs 15 credits; max 10 clones per account. Returns clone.id — use it as voice_id in create_voiceover, create_avatar_video and change_voice. In app-capable hosts the result renders as an interactive panel the user can see and act on — do NOT repeat its contents as a list or table in your reply; add only what the panel doesn't say.
    ConnectorOAuth
  • Walks the workspace's Markdown notes into the search index (chunks, keyword index, entities). If an embedding provider is configured, stamps new and changed notes with it; the provider must match the existing index dimensions. Run it when search_memory or get_context report index.stale; saved facts are keyword-searchable without it. It does not wait for a slow or refusing embedding service: such files are reported (warning "index-unfinished") and finished in the background.
    ConnectorOAuth
  • Pulls fresh comment threads and DMs from the connected platforms (Instagram, Facebook, YouTube, Threads, LinkedIn) into ShortSync's inbox cache. Same operation as clicking the refresh button in the inbox UI. Returns a per-connection DmSyncResult with counts of new conversations and messages plus any errors. Call this before list_inbox_conversations when the user asks for the latest activity — otherwise the tool serves cached data from the last sync. Hits the platform APIs so it counts against rate limits. Threads is beta-gated behind DM_INBOX_THREADS and LinkedIn behind DM_INBOX_LINKEDIN — accounts without the flag see those connections silently skipped rather than an error. LinkedIn coverage is uneven per account: only organization-context connections with r_organization_social can read post comments; personal-profile posts require partner-tier API access we don't have and return no conversations.
    ConnectorOAuth
  • List Delta Meetings for the authenticated organization, newest first, as summary rows: id, title, when, type, status, team, and whether a transcript and a summary exist. Filter by meeting_type or status; with neither, every type is returned. To find the NEXT meeting, pass upcoming=true: only meetings scheduled from now on, soonest first (newest-first plus a limit would otherwise show the furthest-out recurring instances and miss this week's). This tool deliberately does NOT return transcripts or notes -- call get_meeting_transcript or get_meeting_agenda with an id from here for the contents of one meeting.
    ConnectorAPI key
  • Translate existing captions (subtitles or transcriptionJobId) into another language with Workers AI m2m100, keeping cue timing; returns SRT, VTT and JSON. Paid: 2 credits per minute; burn: true also burns the translation into the video (+4 credits/min; needs mediaUrl or fileId and a preset). Word-level highlight timing is not kept. To transcribe, translate and burn in one call use caption_video with translateTo; for a spoken (voice) translation use dub. Saved do-not-translate glossary terms are kept as is. 402 insufficient_balance with checkoutUrl when short; failed jobs refund.
    ConnectorNo auth
  • Transcribe an audio file on your disk (a voice note, a call, a meeting) to text. Returns a one-use URL and a curl command; run it and the response is {"text": ...}. The file never passes through the conversation. A long audio takes minutes: save the response to a file (curl -o) and read it in parts. Up to 25 MB (mp3, m4a, ogg, webm, wav, flac). Spends from the chat budget when the file arrives. For an audio attached to an Odoo record, use odoo_attachment_content. It does not read an audio on Google Drive: download it first.
    ConnectorOAuth
  • Get ready-to-use wording that discloses to a person that they are talking to an AI (AI Act Art. 50(1)). Use this at the start of chat, voice or e-mail conversations an AI agent conducts on behalf of a company. It only returns text; it does not send anything. Not a check of an existing message. Args: firma: company name inserted into the sentence (for example `Muster S.à r.l.`). sprache: `de`, `fr`, `en` or `lb` (case-insensitive). Other values return an error listing the available languages. Returns: `text` (the disclosure sentence), `grundlage`, `pruefstand` (wording is a suggestion; the Luxembourgish version is not reviewed by a native speaker) and `hinweis`. Not legal advice.
    ConnectorNo auth
  • Get ready-to-use wording that discloses to a person that they are talking to an AI (AI Act Art. 50(1)). Use this at the start of chat, voice or e-mail conversations an AI agent conducts on behalf of a company. It only returns text; it does not send anything. Not a check of an existing message. Args: firma: company name inserted into the sentence (for example `Muster S.à r.l.`). sprache: `de`, `fr`, `en` or `lb` (case-insensitive). Other values return an error listing the available languages. Returns: `text` (the disclosure sentence), `grundlage`, `pruefstand` (wording is a suggestion; the Luxembourgish version is not reviewed by a native speaker) and `hinweis`. Not legal advice.
    ConnectorNo auth