Skip to content

settlegrid/settlegrid-assemblyai

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

settlegrid-assemblyai

AssemblyAI MCP Server with per-call billing via SettleGrid.

Powered by SettleGrid License: MIT Deploy with Vercel

Transcribe audio, retrieve transcripts, and generate AI-powered summaries and insights using AssemblyAI's speech-to-text and LeMUR APIs.

Quick Start

npm install
cp .env.example .env   # Add your SettleGrid API key
npm run dev

Methods

Method Description Cost
submit_transcription(audio_url: string, language_code?: string, speaker_labels?: boolean) Submit audio URL for transcription
get_transcription(transcript_id: string) Get transcription result by ID
list_transcriptions(limit?: number) List recent transcripts
get_transcript_sentences(transcript_id: string) Get sentences from a completed transcript
export_transcript(transcript_id: string, format: string) Export transcript in SRT or VTT subtitle format
generate_summary(transcript_ids: string, context?: string) Generate a LeMUR summary of a transcript
ask_lemur(transcript_ids: string, question: string) Ask a question about a transcript using LeMUR
generate_action_items(transcript_ids: string, context?: string) Extract action items from a transcript using LeMUR

Parameters

submit_transcription

  • audio_url (string, required) — Publicly accessible URL of the audio file to transcribe
  • language_code (string) — BCP-47 language code (e.g. 'en', 'es', 'fr'). Defaults to 'en'
  • speaker_labels (boolean) — Whether to enable speaker diarization (default false)

get_transcription

  • transcript_id (string, required) — The ID of the transcript to retrieve

list_transcriptions

  • limit (number) — Maximum number of transcripts to return (default 10, max 50)

get_transcript_sentences

  • transcript_id (string, required) — The ID of the completed transcript

export_transcript

  • transcript_id (string, required) — The ID of the completed transcript
  • format (string, required) — Export format: 'srt' or 'vtt'

generate_summary

  • transcript_ids (string, required) — Comma-separated list of transcript IDs to summarize
  • context (string) — Optional context or instructions to guide the summary

ask_lemur

  • transcript_ids (string, required) — Comma-separated list of transcript IDs to query
  • question (string, required) — The question to answer based on the transcript content

generate_action_items

  • transcript_ids (string, required) — Comma-separated list of transcript IDs to analyze
  • context (string) — Optional context or instructions to guide action item extraction

Environment Variables

Variable Required Description
SETTLEGRID_API_KEY Yes Your SettleGrid API key from settlegrid.ai
ASSEMBLYAI_API_KEY Yes AssemblyAI API key from https://www.assemblyai.com/dashboard

Upstream API

Deploy

Docker

docker build -t settlegrid-assemblyai .
docker run -e SETTLEGRID_API_KEY=sg_live_xxx -p 3000:3000 settlegrid-assemblyai

Vercel

Click the "Deploy with Vercel" button above, or:

npm run build
vercel --prod

License

MIT - see LICENSE


Built with SettleGrid — The Settlement Layer for the AI Economy

About

MCP server for AssemblyAI with SettleGrid billing. Transcribe audio, retrieve transcripts, and generate AI-powered summaries and insights using AssemblyAI's speech-to-text and LeMUR APIs.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors