Deepgram for Claude, Cursor, ChatGPT & agents

Deepgram — transcribe audio (speech-to-text) from URLs or local files with diarization, punctuation, smart formatting, and language detection (nova-3 / nova-2), and synthesize speech (text-to-speec...

curl -fsSL https://syncorelabs.ai/install.sh | sh

What it does

Deepgram — transcribe audio (speech-to-text) from URLs or local files with diarization, punctuation, smart formatting, and language detection (nova-3 / nova-2), and synthesize speech (text-to-speech) with Aura voices to MP3 / WAV / opus / FLAC. Use when the user mentions Deepgram, ASR, STT, TTS, transcribe, voice, audio, podcast, transcript, voiceover, or wants to convert audio↔text.

The Deepgram skill is one of 75+ pre-wired Syncore integrations that any MCP-compatible client — Claude Desktop, Claude Code, Cursor, Windsurf, Codex CLI, and ChatGPT desktop — can call out of the box. You don't configure MCP servers or copy API keys into a JSON file; the Syncore daemon discovers the skill at startup and exposes its tools to whichever AI client is running.

Sample prompts

Once Syncore is installed and Deepgram is connected, ask your agent something like:

• “Transcribe this audio file with speaker diarization.”
• “Speak this paragraph as MP3 using a natural female voice.”
• “Transcribe https://example.com/podcast.mp3 and return a clean transcript.”

Tools available (3)

• deepgram__transcribe_url

  Transcribe / convert speech-to-text on a remote audio or video URL via Deepgram. Use when the user wants to transcribe a podcast, YouTube audio, hosted recording, or any HTTPS-served media. Supports model (nova-3 default), language (BCP-47 or 'multi'), diarize, punctuate, smart_format.

• deepgram__transcribe_file

  Transcribe / convert a local audio or video file (path on disk) to text via Deepgram. Use when the user wants to transcribe a recording from their machine. Same options as transcribe_url — model, language, diarize, punctuate, smart_format.

• deepgram__speak

  Synthesize / generate / read aloud speech from text using Deepgram Aura voices (aura-asteria-en, aura-luna-en, aura-stella-en, aura-athena-en). Use when the user wants TTS, voiceover, or to hear text spoken. Default writes MP3 to a temp file and returns path; pass response_format: b64_json for inline base64 (sandboxed

How to connect

Deepgram needs a provider API key to talk to deepgram. Connect it from the Syncore dashboard:

1. Run curl -fsSL https://syncorelabs.ai/install.sh | sh on macOS / Linux (or the PowerShell command on Windows).
2. Run syncore login to create your account and a device-bound encryption key.
3. Visit syncorelabs.ai/connect and authorize Deepgram.
4. Run syncore update to sync the skill + credentials to every installed AI client.

Pricing

Included on every Syncore tier with a per-tier shared quota — Free covers light use; Pro at $29/mo and Ultra at $99/mo unlock larger monthly allowances. Bring your own provider API key any time to bypass the Syncore quota.

See the full Syncore pricing breakdown — Free $0/mo, Pro $29/mo, Ultra $99/mo — on the homepage.