deepgramOfficial·8 Agent Skills Included

deepgram-python-sdk

Python speech transcription, text-to-speech, and voice agent integration

Integrates Deepgram speech recognition, text-to-speech, and text analysis into Python applications. Covers live streaming transcription, speaker diarization, sentiment analysis, and full-duplex voice agents with function calling. Eliminates guesswork around authentication schemes, WebSocket lifecycle, and model selection with tested code patterns. Helps developers ship voice features faster with correct sync and async client usage.

456|139

↗

npx skills add deepgram/deepgram-python-sdk --all -g -y

All Skills in This Repository (8)

Pure Emerald Level Indicators

📦 In Repo

deepgram

deepgram-python-speech-to-text

Transcribe audio files and streams using the Deepgram Python SDK.

deepgram-python-voice-agent

Builds a real-time voice agent using the Deepgram Python SDK and WebSocket protocol.

deepgram-python-text-to-speech

Implement and review Python code using Deepgram Text-to-Speech v1 APIs.

deepgram-python-conversational-stt

Implement turn-aware streaming transcription with Deepgram Conversational STT v2 Flux in Python.

deepgram-python-management-api

Automate Deepgram resource management with the Python SDK.

deepgram-python-text-intelligence

Analyze Python code using Deepgram Read API for sentiment, topics, and intents.

deepgram-python-audio-intelligence

Enable Deepgram STT analytics overlays for summaries, topics, intents, sentiment, diarization, redaction, and language detection via the Python SDK.

deepgram-python-maintaining-sdk

Regenerate Fern-based Python SDKs and reconcile manual patches.

Official

Advanced

Frequently Asked Questions

FAQPage Schema

How to install deepgram-python-sdk?▼

Run `npx skills add deepgram/deepgram-python-sdk --all -g -y` in your terminal to install all skills in this suite globally.

How to transcribe audio files in Python?▼

Use the speech-to-text skill patterns: call `client.listen.v1.media.transcribe_file` with your audio bytes and a model like nova-3, then read the transcript from the response.

How to build a voice agent in Python?▼

The voice agent skill shows how to connect over WebSocket, send settings for listen, think, and speak providers, and handle events like user speech and function calls.

Does the Deepgram SDK support async Python?▼

Yes. The SDK provides an AsyncDeepgramClient with full async/await support for transcription, text-to-speech, and streaming WebSocket connections.

How to add sentiment analysis to audio transcription?▼

Enable analytics flags like sentiment, summarize, topics, and diarize on the standard transcription request; the audio intelligence skill covers the exact parameters and REST-only limitations.