The Speak AI MCP server exposes 189 tools across 18 categories. Every tool has its own page with a plain-language summary, its parameters, and its behaviour hints.
These pages are generated from the server’s own tool manifest and its input schemas,
so they change when the server changes. Fix a wrong description in the speak-mcp
repo, not here.
Showing 189 of 189 tools.
No tools match your search. Try a different term.
What does the Media category cover?
Upload audio or video, fetch transcripts, get AI insights, organize, favorite, export. The Media category has 19 tools, each on its own page under Media.
update_transcription: Edit the official transcript text of a single media file by finding and replacing text.get_signed_upload_url: Get a pre-signed S3 URL for direct file upload to Speak AI storage.upload_media: Import an audio or video file into Speak AI from a URL and start transcription.upload_local_file: Upload a local file to Speak AI for transcription and analysis.upload_and_analyze: Upload and transcribe media from a URL: a direct/public file URL, OR a shareable social/video page link, which Speak resolves to the underlying media automatically.list_media: List and search media files in the workspace with filtering, pagination, and sorting.get_media_insights: Retrieve AI-generated insights for a processed media file: topics, sentiment, keywords, action items, summaries, and more.get_transcript: Retrieve the full transcript for a media file with speaker labels and timestamps.get_captions: Get captions for a media file.update_transcript_speakers: Update or rename speaker labels in a single media transcript.bulk_update_transcript_speakers: Normalise speaker names that are ALREADY correct across multiple media files: for example changing “Frederik S.” to “Frederik” everywhere.get_media_status: Check the processing status of a media file.update_media_metadata: Update metadata fields (name, description, tags, status) for an existing media file.delete_media: Permanently delete a media file and all associated transcripts and insights.toggle_media_favorite: Mark or unmark media files as favorites for quick access.reanalyze_media: Re-run AI analysis on a media file using the latest models.bulk_move_media: Move multiple media files to a folder in a single operation.upload_and_analyze_batch: Import up to 25 audio or video URLs in one call.set_media_thumbnail: Set a custom thumbnail for a video.
What does the AI Chat category cover?
Run AI prompts across one file, a folder, or your whole workspace. Save favorites. The AI Chat category has 13 tools, each on its own page under AI Chat.
ask_ai_chat: Ask an AI-powered question about your media using Speak AI’s AI Chat.retry_ai_chat: Retry a failed or incomplete AI Chat response.get_chat_history: Get a list of recent AI Chat conversations.get_chat_messages: Get full message history for conversations.delete_chat_conversation: Delete an entire chat conversation from conversation history, so it and its messages no longer appear.list_prompts: List recent AI Chat messages across the workspace, newest first, with each prompt, answer, references, and the media or folder it ran on.get_favorite_prompts: Get all prompts and answers that have been marked as favorites.toggle_prompt_favorite: Mark or unmark a chat message as a favorite for easy retrieval later.update_chat_title: Update the title of a chat conversation for easier identification in history.submit_chat_feedback: Submit feedback on a chat response (thumbs up/down).get_chat_statistics: Get usage statistics for AI Chat / chat.export_chat_answer: Export a specific AI Chat answer.get_analysis_quote: Check whether a media file can be analysed as audio or video, and what it will cost, before runningask_ai_chatwith analysisInput.
What does the Search & analytics category cover?
Full-text search across transcripts, insights, and metadata. Workspace-level stats. The Search & analytics category has 3 tools, each on its own page under Search & analytics.
search_media: Deep search across all media transcripts, insights, and metadata.get_media_statistics: Get workspace-level media statistics: total counts, processing status breakdown, storage usage, etc.list_supported_languages: List all languages supported for transcription.
What does the Folders & views category cover?
Create folders, save filtered views, bulk move files, share read-only collections. The Folders & views category has 11 tools, each on its own page under Folders & views.
list_folders: List all folders in the workspace with pagination and sorting.get_folder_info: Get detailed information about a specific folder including its contents.create_folder: Create a new folder in the workspace, optionally assigned to users or user groups.clone_folder: Create a new folder copied from an existing folder’s name and description.update_folder: Update a folder.delete_folder: Permanently delete a folder.get_all_folder_views: Retrieve all saved views across all folders.get_folder_views: Retrieve all saved views for a specific folder.create_folder_view: Create a new saved view for a folder with a custom set of display columns.update_folder_view: Update an existing saved view.clone_folder_view: Duplicate an existing folder view into a target folder.
What does the Recorders & surveys category cover?
Public recording links for clients, prompted question sets, branded submission pages. The Recorders & surveys category has 10 tools, each on its own page under Recorders & surveys.
create_recorder: Create a new recorder or survey for collecting audio/video submissions.list_recorders: List all recorders/surveys in the workspace.get_recorder_info: Get detailed information about a specific recorder including its settings and questions.clone_recorder: Duplicate an existing recorder including all its settings and questions.get_recorder_recordings: List all submissions/recordings collected by a specific recorder.generate_recorder_url: Retrieve the existing shareable URL and embed iframe code for a recorder/survey.update_recorder_settings: Update configuration settings for a recorder (branding, capture options, etc.).update_recorder_questions: Update the survey questions and respondent-info settings for a recorder.check_recorder_status: Check whether a recorder/survey is active and accepting submissions.delete_recorder: Permanently delete a recorder/survey.
What does the Clips category cover?
Highlight clips from any time range. Export PDF, DOCX, SRT, VTT, TXT, CSV. The Clips category has 4 tools, each on its own page under Clips.
create_clip: Create a highlight clip from one or more media files by specifying time ranges.get_clips: List clips, optionally filtered by folder or media files.update_clip: Update a clip’s title, description, or tags.delete_clip: Permanently delete a clip and its associated media file.
What does the Exports category cover?
Highlight clips from any time range. Export PDF, DOCX, SRT, VTT, TXT, CSV. The Exports category has 2 tools, each on its own page under Exports.
export_media: Export a media file’s transcript, insights or labels in various formats (pdf, docx, srt, vtt, txt, csv).export_multiple_media: Export multiple media files at once, optionally merged into a single file.
What does the Meeting assistant category cover?
Schedule Speak AI to join a Zoom / Google Meet / Teams call and transcribe automatically. The Meeting assistant category has 5 tools, each on its own page under Meeting assistant.
list_meeting_events: List scheduled or completed meeting assistant events with filtering and pagination.schedule_meeting_event: Schedule the Speak AI meeting assistant to join and record an online meeting (Zoom, Google Meet, Microsoft Teams, or Webex).remove_assistant_from_meeting: Remove the Speak AI assistant from an active or scheduled meeting.delete_scheduled_assistant: Cancel and delete a scheduled meeting assistant event.get_live_meeting_transcript: Fetch new sentences from an in-progress or just-ended meeting transcript.
What does the Automations category cover?
Trigger actions on new recordings. Send events to your own backend. The Automations category has 20 tools, each on its own page under Automations.
list_automations: List automation rules in the workspace, with paging and filters.get_automation: Get detailed information about a specific automation rule, including its trigger and step graph.create_automation: Create an automation: a trigger plus ordered steps (V2 graph model).update_automation: Update an existing automation rule.toggle_automation_status: Toggle an automation rule between active and inactive.list_automation_names: List the names and ids of active automations that contain an AI chat (magic prompt) step.get_automation_runs: Get the run history (executions) for an automation, with paging and optional status filter.bulk_update_automation_status: Activate or deactivate multiple automations at once.bulk_assign_automation_folders: Set the folder scope for multiple automations at once.run_automations: Manually run one or more automations against one or more media items now (outside the normal trigger).delete_automation: Permanently delete an automation rule.list_automation_apps: List the apps in Speak’s automation catalog: Speak’s built-in apps plus, when enabled, third-party apps available through Composio, each marked connected or not_connected for this user.list_automation_triggers: List the trigger types available in the automation catalog.list_automation_actions: List the step types (actions) available in Speak’s automation catalog, optionally for one app slug, plus the fields each filter or condition step can test.build_automation: High-level automation builder: create (or update) a Speak automation from a friendly spec without knowing the wire format.get_automation_run: Get one automation run in full: every step, in dependency order, with what it produced and why it stopped.get_automation_run_stats: Aggregate run counts for an automation over a period: how many completed, failed, or were stopped.test_automation: Run one automation once against one media item to see which way it branches.validate_automation_graph: Check a step graph without saving anything.describe_automation_graph: Show a saved automation’s steps as an indented branch tree instead of a flat list.
What does the Webhooks category cover?
Trigger actions on new recordings. Send events to your own backend. The Webhooks category has 7 tools, each on its own page under Webhooks.
create_webhook: Create an outbound webhook.list_webhooks: List all configured webhooks in the workspace.update_webhook: Update an existing webhook.delete_webhook: Permanently delete an outbound webhook and its delivery attempt history; its endpoint stops receiving notifications.provision_inbound_webhook: Provision a standalone inbound webhook and get its public receive URL (inboundUrl) BEFORE creating an automation.get_inbound_webhook: Get an inbound webhook’s public receive URL, captured sample payload, and the ready-to-paste {{trigger.payload.*}} tokens for mapping payload values into automation steps (speak-upload name/sourceUrl, fieldsMap custom-field values, notify/outbound-webhook templates).get_webhook_attempts: Get the delivery log for an inbound webhook: each received request with its HTTP acknowledgement status (200 = sample captured, 202 = accepted and run started, 401/403 = rejected) and the automation run it started.
What does the Text notes category cover?
Standalone AI-analyzed text notes plus custom fields you can tag any media file with. The Text notes category has 4 tools, each on its own page under Text notes.
create_text_note: Create a new text note in Speak AI for analysis.get_text_insight: Retrieve AI-generated insights for a text note, including topics, sentiment, summaries, and action items.reanalyze_text: Trigger a re-analysis of an existing text note to regenerate insights with the latest AI models.update_text_note: Update an existing text note’s name, content, or metadata.
What does the Fields category cover?
Define the fields you tag media files with, and set their values. The Fields category has 4 tools, each on its own page under Fields.
list_fields: List all custom fields defined in the workspace.create_field: Create a new custom field for categorizing and tagging media.update_field: Update a specific custom field by ID.update_multiple_fields: Set custom field values across media in a single batch operation, overwriting existing values.
What does the Labels & comments category cover?
Manage workspace labels, apply them to transcript words, and discuss a file in comment threads. The Labels & comments category has 16 tools, each on its own page under Labels & comments.
list_labels: List the workspace’s labels as a tree: groups (isGroup true) carry their labels inlabels, and ungrouped labels sit at the top level.create_label: Create a label, or a label group with isGroup true.update_label: Rename, recolor, describe, move or reorder a label or group.archive_label: Archive a label so it can no longer be applied; archiving a group archives its labels too.restore_label: Restore an archived label; restoring a group also restores its archived labels.merge_labels: Merge one label into another: every place the source label is applied moves onto the target (a span that had both keeps one), then the source is archived with mergedInto set.add_speak_label_sets: Add ready-made label groups from Speak: sales_qa (Unprofessional, Slang, Objection, Great moment, Compliance risk), research (Pain point, Motivation, Quote for report, Surprise, Follow-up), meetings (Decision, Action item, Risk, Open question) and transcript_feedback (Wrong split, Misheard word, Wrong speaker, Bad translation).list_media_labels: List the labels applied to a media file’s transcript, in transcript order, with the file’s current transcriptRevision.apply_label: Apply one or more labels to a span of words in a media file’s transcript.update_media_label: Change a labelled span on a transcript.remove_media_label: Remove a labelled span from a transcript.list_media_comments: List the comment threads on a media file, with the file’s current transcriptRevision.add_comment: Add a comment to a media file.update_comment: Edit the text of a comment.resolve_comment: Resolve a comment thread, or reopen it with resolved false.delete_comment: Delete a comment.
What does the Embed players category cover?
Embeddable player widgets for media on your own website. The Embed players category has 7 tools, each on its own page under Embed players.
create_embed: Create an embeddable player/transcript widget for a media file or a set of folders.update_embed: Update an existing embed widget: appearance/feature toggles viameta, and privacy.check_embed: Check if an embed exists for a media file and retrieve its configuration.get_embed_iframe_url: Get the iframe URL for embedding a media player/transcript on a webpage.list_embed_sessions: Owner analytics for an embed: list the visits (sessions) to one embed, newest first by default.get_embed_session_summary: Owner analytics for an embed: totals across its visits for a date range.get_embed_session: Owner analytics for an embed: one visit in full.
What does the Users & teams category cover?
List workspace members and manage user groups. The Users & teams category has 5 tools, each on its own page under Users & teams.
list_users: List the users (members) in the workspace/company, with their ids, names, emails, and permissions.list_user_groups: List all user groups in the company.create_user_group: Create a new user group and assign members.update_user_group: Update a user group’s name and member list.delete_user_group: Permanently delete a user group.
What does the Dashboards category cover?
Create and manage analytics dashboards, widgets, and public sharing. The Dashboards category has 9 tools, each on its own page under Dashboards.
list_dashboard_widgets: Discovery + how-to helper for building and customizing dashboards.list_dashboards: List all analytics dashboards the caller can access, including share state and each dashboard’s currentrevision(needed forupdate_dashboard).get_dashboard: Get a single dashboard’s full spec: title, description, source, date range, sections, widgets, and the currentrevision(pass that revision back toupdate_dashboard).create_dashboard: Create an analytics dashboard.update_dashboard: Update a dashboard.delete_dashboard: Soft-delete a dashboard.duplicate_dashboard: Clone an existing dashboard into a new dashboard owned by the caller.share_dashboard: Enable public sharing for a dashboard and return its share token + embed id.get_dashboard_speakers_insight: Compute a speakers breakdown for a given folder scope, date range, and field filters.
What does the Voice agents category cover?
Create and configure voice agents, the questions they ask callers and their test suites, and review their conversations. The Voice agents category has 34 tools, each on its own page under Voice agents.
list_voice_agents: List the voice agents in the company (newest first).get_voice_agent: Fetch a single voice agent by its agentId.create_voice_agent: Create a voice agent.update_voice_agent: Update a voice agent.delete_voice_agent: Delete a voice agent.create_voice_agent_from_prompt: Create a new voice agent from a plain-English description, via an LLM call.generate_voice_agent_config: Run the same prompt-to-config generation ascreate_voice_agent_from_prompt, but against an existing agent instead of creating a new one.get_voice_agent_setup_guide: Discovery + how-to helper for building and operating a Speak AI voice agent end to end.list_voice_avatars: List the video avatars available to attach to a voice agent (your company’s own uploads plus the shared system catalog).list_voices: List the text-to-speech voices available to a voice agent.list_voice_conversations: List the company’s voice conversations (newest first).get_voice_conversation: Fetch a single voice conversation by its conversationId, including transcript, usage, costs, and analysis.get_agent_analytics: Owner analytics for one voice agent over a date range.list_voice_questions: List the questions configured on a voice agent, in the order it asks them.get_voice_question: Fetch a single voice agent question by its fieldId, scoped to your company.create_voice_question: Attach a question template to a voice agent.update_voice_question: Partially update a voice agent question: only the fields you send are changed.delete_voice_question: Permanently remove a question from a voice agent and decrement the underlying template’s usageCount.reorder_voice_questions: Set the order a voice agent asks its questions in.list_voice_question_templates: List the question templates visible to your company: Speak’s shared system templates, plus your own company’s templates.create_voice_question_template: Create a company-scoped question template: the “custom question” a user names themselves rather than picking from Speak’s shared library.get_voice_test_suite: Get a voice agent’s test suite (its scenarios and run settings).update_voice_test_suite: Create or update a voice agent’s test suite.generate_voice_test_suite: Auto-generate a default test suite for a voice agent from its configuration (name, personality, instructions, welcome message, topics to avoid), via an LLM call.start_voice_test_run: Start a test run of a voice agent’s scripted test suite.get_active_voice_test_run: Get a voice agent’s currently active test run (queued, running, or paused).pause_voice_test_run: Pause a voice agent’s test run.resume_voice_test_run: Resume a paused voice agent test run, transitioning it back to running.cancel_voice_test_run: Cancel a voice agent test run.list_voice_test_runs: List a voice agent’s test runs, most recent first.get_voice_test_run: Get a test run’s full detail, including scenarioResults and recommendations.apply_voice_test_recommendation: Apply a test run recommendation’s quick action to the agent (e.g. patch_instructions appends the suggested fix to the agent’s instructions).get_voice_test_baseline: Get a voice agent’s best-scoring completed test run, used to detect regressions on later runs.get_voice_test_score_history: Get completed-run score points for a voice agent, most recent first, for charting.
What does the Voice agent insights category cover?
Review and act on a voice agent’s self-improvement surface: knowledge gaps, FAQ suggestions, instruction gaps, and its knowledge-base resources. The Voice agent insights category has 16 tools, each on its own page under Voice agent insights.
list_voice_kb_gaps: List a voice agent’s pending knowledge-base gaps: questions callers asked that the agent answered with low confidence or an explicit “I don’t know,” surfaced automatically after calls.analyze_voice_kb_gaps: Trigger knowledge-base gap analysis over a voice agent’s recent calls.add_voice_kb_gap: Write a knowledge-base gap’s answer into the voice agent’s attached knowledge base as a new document, and mark the gap added.dismiss_voice_kb_gap: Mark a voice agent’s knowledge-base gap dismissed without writing anything to the knowledge base.list_voice_faq_suggestions: List a voice agent’s pending FAQ suggestions: questions multiple callers asked in similar form, clustered and drafted into a reusable question/answer pair.generate_voice_faq_suggestions: Trigger FAQ clustering over a voice agent’s recent calls.add_voice_faq_suggestion: Write an FAQ suggestion’s question/answer into the voice agent’s attached knowledge base as a new document, and mark the suggestion added.update_voice_faq_suggestion: Edit a still-pending FAQ suggestion’s question and/or answer before adding it.dismiss_voice_faq_suggestion: Mark a voice agent’s FAQ suggestion dismissed without writing anything to the knowledge base.list_voice_agent_resources: List the knowledge documents/links a voice agent searches during calls: separate from KB gaps and FAQ suggestions, which are the self-improvement layer that surfaces what an agent is missing, not the content itself.create_voice_agent_resource: Add one document/link to a voice agent’s knowledge base.bulk_create_voice_agent_resources: Add up to 100 documents/links to a voice agent’s knowledge base in one call.update_voice_agent_resource: Partially update a voice agent resource: send at least one field.delete_voice_agent_resource: Soft-delete a voice agent resource: it stops appearing in lists and the agent stops searching it, but the document is not physically removed.analyze_voice_instruction_gaps: Advisory only: compares a voice agent’s current instructions against anchors/original intent/recent call summaries you supply and suggests up to 3 patches.apply_voice_instruction_gap: Insert a suggested instruction patch into a voice agent’s instructions and persist the result.
Related
- MCP server covers setup, supported clients, and what agents can do once connected.