Deepgram Python Audio Intelligence
- 25 installs
- 454 repo stars
- Updated August 3, 2026
- deepgram/deepgram-python-sdk
Overlay Deepgram audio analytics (summarize, topics, intents, sentiment, diarize, redact, language detection) on /v1/listen transcription from Python.
About
A Python SDK skill for enabling Deepgram audio-intelligence overlays on the /v1/listen endpoint - summarization, topic and intent detection, sentiment, speaker diarization, PII redaction, and language detection - via the same client.listen methods used for plain transcription. Reach for it when you have audio (file, URL, or live stream) and need analytics alongside the transcript, and want to know which features are REST-only versus available over WebSocket.
- Analytics overlays on /v1/listen: summarize, topics, intents, sentiment
- Diarization, PII redaction, and entity/language detection
- REST (transcribe_url/transcribe_file) plus the WSS-supported subset
- REST vs WSS feature matrix so you pick the right transport
Deepgram Python Audio Intelligence by the numbers
- 25 all-time installs (skills.sh)
- Ranked #9,764 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/deepgram/deepgram-python-sdk --skill deepgram-python-audio-intelligenceAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 25 |
|---|---|
| repo stars | ★ 454 |
| Last updated | August 3, 2026 |
| Repository | deepgram/deepgram-python-sdk ↗ |
What it does
Overlay Deepgram audio analytics (summarize, topics, intents, sentiment, diarize, redact, language detection) on /v1/listen transcription from Python.
Who is it for?
Adding analytics (summaries, sentiment, diarization) to an audio transcription pipeline in Python
Skip if: Plain transcription with no analytics, or analyzing already-transcribed text
When should I use this skill?
Calling Deepgram /v1/listen with analytics params from Python
What you get
Correctly configured Deepgram audio-intelligence calls that return transcript plus analytics.
- Python code calling Deepgram audio-intelligence features
By the numbers
- Analytics like summarize/topics/intents/sentiment are REST-only; diarize/redact work over WSS
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
Can I get summaries over WebSocket?
No - summarize, topics, intents, sentiment, and language detection are REST-only; diarize and redact work over WSS.
Is this the same endpoint as plain STT?
Yes, /v1/listen with the same client methods - you just enable analytics via params.