MCP Hub
Back to servers

Descript Complete

Provides full Descript integration for transcription, AI-powered editing, voice synthesis, and export. Automates audio/video processing including filler word removal, silence trimming, and project collaboration through natural language commands.

glama
Updated
Apr 3, 2026

Descript Complete MCP Server

Stop manually transcribing audio. Upload recordings, get transcripts, remove filler words, and export edited content — all from your AI assistant.

What It Does

This MCP server gives your AI assistant full control over Descript: transcription, editing, AI voice (Overdub), collaboration, and export — all via natural language.

Tools

ToolCategoryDescription
transcribe_audioTranscriptionSubmit an audio URL for transcription
transcribe_videoTranscriptionSubmit a video URL for transcription
get_transcriptTranscriptionFetch transcript by share slug (text, JSON, or VTT)
list_transcriptsTranscriptionList recent transcription jobs
create_projectProjectsCreate a new Descript project
list_projectsProjectsList all projects in your account
get_projectProjectsGet details for a specific project
delete_projectProjectsDelete a project permanently
upload_mediaMediaUpload media to a project via URL
get_upload_statusMediaCheck upload/processing job status
remove_filler_wordsEditingRemove um, uh, like, etc. with AI
remove_silenceEditingRemove silent gaps automatically
trim_transcriptEditingEdit content via natural language instruction
export_transcript_txtExportExport transcript as plain text
export_transcript_srtExportExport transcript as SRT subtitles
export_videoExportRender/export the video
create_overdubOverdubGenerate speech with AI voice
list_overdub_voicesOverdubList available AI voices
get_project_membersCollaborationGet project collaborators
share_projectCollaborationInvite a collaborator by email

Quick Start

  1. Get your Descript API key from your Descript account settings
  2. Set DESCRIPT_API_KEY=your_key_here in your environment
  3. Start the server: npm start
  4. Connect your MCP client to http://localhost:8080/mcp

Example Workflows

Transcribe a podcast episode:

transcribe_audio({ url: "https://example.com/episode-42.mp3", project_name: "Episode 42" })
// Returns job_id — poll with get_upload_status until state = "stopped"
// Then get_transcript({ slug: "your-share-slug", format: "text" })

Clean up an interview recording:

remove_filler_words({ project_id: "abc123" })
remove_silence({ project_id: "abc123", threshold_seconds: 0.8 })
export_transcript_txt({ slug: "your-share-slug", include_speakers: true })

Share for review:

share_project({ project_id: "abc123", email: "editor@example.com", role: "editor" })

Environment Variables

VariableRequiredDescription
DESCRIPT_API_KEYYesYour Descript API key
PORTNoServer port (default: 8080)

Health Check

GET http://localhost:8080/health
# {"status":"ok","server":"descript-complete","version":"1.0.0"}

Built with the MCPize framework. Powered by mastermindshq.business.

Reviews

No reviews yet

Sign in to write a review