Scriptivox

AI transcription from URLs or local files: 119 languages, speaker diarization, word-level timestamps, SRT/VTT/text export.

@scriptivox/mcp-server

smithery badge

MCP (Model Context Protocol) server for Scriptivox — AI-powered audio and video transcription.

Turn any AI assistant into a transcription powerhouse. Transcribe audio and video from URLs or local files with 99% accuracy, speaker diarization, 119 languages, and word-level timestamps. Plus full CRUD on transcriptions (cancel, delete, list) and caption export in SRT / WebVTT / plain text.

Quick Start

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "scriptivox": {
      "command": "npx",
      "args": ["-y", "@scriptivox/mcp-server"],
      "env": {
        "SCRIPTIVOX_API_KEY": "sk_live_YOUR_KEY"
      }
    }
  }
}

Claude Code

claude mcp add scriptivox -- npx -y @scriptivox/mcp-server

Then set the environment variable SCRIPTIVOX_API_KEY=sk_live_YOUR_KEY.

Other MCP Clients

Any MCP-compatible client can use this server via stdio transport:

SCRIPTIVOX_API_KEY=sk_live_YOUR_KEY npx -y @scriptivox/mcp-server

Getting an API Key

  1. Sign up at platform.scriptivox.com
  2. Go to Keys in the dashboard
  3. Create an API key (starts with sk_live_...)
  4. Add credits at Billing ($5 minimum — API pricing is $0.20/hour of audio)

Tools

Discovery tools (no API key required)

ToolDescription
get_supported_languagesList all 119 supported transcription languages with ISO codes
get_pricingView plans, API pricing, and per-file limits
get_product_infoLearn about Scriptivox features (transcription, audio-tools, video-tools, subtitle-tools, meeting-bot, api, all)
get_api_docsAPI documentation sections (quickstart, transcribe, result, list, cancel, delete, upload, balance, webhooks, errors, all)

Transcription tools (API key required)

ToolDescription
transcribe_urlTranscribe audio/video from a public URL (Google Drive, Dropbox, OneDrive, or direct file URLs). Supports language, diarize, speaker_count, align, webhook_url, idempotency_key, await_completed.
transcribe_uploadTranscribe a LOCAL file. Drives the 3-step upload flow internally. Up to 5 GB.
transcribe_statusCheck the status of a transcription by ID. Returns the full transcript when completed.
transcribe_cancelCancel an in-flight transcription. Refunds reserved balance. Idempotent.
transcribe_deleteSoft-delete a transcription record. Idempotent. Refuses to delete in-flight jobs.
list_transcriptionsList recent transcriptions with status, from, to, limit, cursor, order filters.
export_transcriptExport a completed transcript as SRT subtitles, WebVTT subtitles, or plain text. Segmentation knobs: max_words, max_chars, max_duration, sentence_aware, include_speakers, strip_chars.
check_balanceView your API credit balance and estimated hours available.

Tip: always pass language when you know it

Auto-detection works in most cases but has a small failure rate on short clips, code-switched audio, or files starting with music. Passing the ISO code is both faster and more accurate.

Usage examples

Once connected, ask your AI assistant:

  • "Transcribe this podcast: https://example.com/episode.mp3 — it's in English"
  • "Transcribe ~/Downloads/meeting.m4a with speaker identification"
  • "Show me my last 5 transcriptions"
  • "Cancel transcription abc123-…"
  • "Export transcription abc123-… as SRT subtitles, 2 words per caption"
  • "What languages does Scriptivox support?"
  • "Check my Scriptivox balance"

Resources

The server exposes these MCP resources for AI assistants to read:

  • scriptivox://pricing — Plans and rates
  • scriptivox://languages — Supported languages
  • scriptivox://api-docs — API reference

Prompts

  • transcribe-audio — Pre-built prompt for URL transcription
  • meeting-notes — Transcribe a meeting and generate structured notes

Configuration

Environment VariableDescriptionRequired
SCRIPTIVOX_API_KEYYour API key (sk_live_...)For transcription tools
SCRIPTIVOX_API_URLCustom API base URLNo (defaults to production)

Pricing

  • Free plan: 3 transcriptions/day, 30 min max
  • Pro plan: $20/month — unlimited transcriptions
  • API: $0.20/hour of audio (pay-as-you-go)

Links

License

MIT

Related Servers