deepgram-sdk

What it is and what it does

The Deepgram Python SDK is the official client library for accessing Deepgram's speech and language AI services. It wraps HTTP and WebSocket APIs for speech-to-text transcription (file and real-time), text-to-speech synthesis, text analysis (sentiment, topics, intents), and voice agent orchestration. The SDK provides both synchronous and asynchronous clients, supports two authentication methods (API key and access token), and handles connection management and event streaming internally.

You use it to add speech recognition, voice synthesis, or conversational AI capabilities to Python applications without building HTTP clients or managing WebSocket connections yourself. It depends on httpx for HTTP transport, pydantic for request/response validation, and websockets for real-time streaming. The library is actively maintained, supports Python 3.10 through 3.15, and has no known security vulnerabilities.

Use it for:

• Transcribe pre-recorded audio files to text using the file transcription API with models like nova-3.
• Build real-time speech recognition applications using WebSocket connections with the Listen v2 model.
• Generate natural-sounding speech from text and save it as audio files using the text-to-speech API.
• Analyze text for sentiment, topics, and intent detection in language understanding workflows.
• Create conversational voice agents that combine speech recognition, LLM reasoning, and speech synthesis.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Official Python SDK for Deepgram's speech recognition, text-to-speech, language understanding, and voice agent APIs, with synchronous and asynchronous client support.

Yes. The SDK is actively maintained (released 2 days ago), has low install friction, no known vulnerabilities, and a permissive MIT license. It's the official client for Deepgram's APIs and covers a complete feature set from transcription to voice agents. Install it if you need to integrate Deepgram's speech or language AI services into a Python application.

Install

deepgram-sdk on PyPI

pip install deepgram-sdk

uv add deepgram-sdk

poetry add deepgram-sdk

Installing deepgram-sdk

Before you install

Low install friction with a pure-Python wheel distribution. Active maintenance with a release 2 days old and last commit on 2026-08-14. Depends on five well-established packages: httpx, pydantic, pydantic-core, typing_extensions, and websockets.

License in practice

MIT license (permissive) means you can use, modify, and distribute this package freely in commercial and private projects with minimal restrictions.

Quickstart

pip install deepgram-sdk

from deepgram import DeepgramClient

client = DeepgramClient(api_key="YOUR_API_KEY")
with open("audio.wav", "rb") as audio_file:
    response = client.listen.v1.media.transcribe_file(
        request=audio_file.read(),
        model="nova-3"
    )
    print(response.results.channels[0].alternatives[0].transcript)

Requires a Deepgram API key (via DEEPGRAM_API_KEY environment variable or explicit parameter) and Python 3.10 or later.

Verify before relying

• Whether the SDK's WebSocket connections (Listen v2, Speak v1, Agent v1) work reliably in production environments at scale.
• Performance characteristics and latency for real-time streaming use cases.
• Completeness of error handling and recovery for network interruptions.

Package facts

Evidence: deepgram_sdk-7.7.0-py3-none-any.whl

Tags

More Python Modules packages