docs: add strands-deepgram to Community Packages

[eraykeskinmac]

Proposed Content
I would like to propose adding strands-deepgram to the Community Packages documentation.

This is a production-ready speech and audio processing tool for Strands Agents, powered by Deepgram's AI platform. It enables agents to transcribe audio with 30+ language support, generate natural-sounding speech, and perform advanced audio intelligence analysis.

Key Features:

• 🎤 Speech-to-Text: 30+ language support and speaker diarization
• 🗣️ Text-to-Speech: Natural-sounding voices (Aura series)
• 🧠 Audio Intelligence: Sentiment analysis, topic detection, and intent recognition
• 👥 Speaker Diarization: Identify and separate different speakers
• 🎵 Multi-format Support: WAV, MP3, M4A, FLAC, and more
• ⚡ Real-time Processing: Streaming capabilities for live audio

Package Information:

• PyPI: https://pypi.org/project/strands-deepgram/
• GitHub: https://github.com/eraykeskinmac/strands-deepgram
• Version: 0.1.0 (Production-ready)
• Examples: https://github.com/eraykeskinmac/strands-tools-examples

Installation:

pip install strands-deepgram
pip install 'strands-agents[anthropic]'

Quick Usage Example:

from strands import Agent
from strands_deepgram import deepgram

agent = Agent(tools=[deepgram])

# Transcribe with speaker identification
agent("transcribe this audio: recording.mp3 with speaker diarization")

# Text-to-speech
agent("convert this text to speech: Hello world")

# Audio intelligence
agent("analyze sentiment in call.wav")

Location
Community Packages → Tools → Speech & Audio Processing

Rationale
This package would be valuable for the Strands Agents community because:

1. Fills a Critical Gap: Enables AI agents to process voice and audio data, which is essential for modern applications like call analytics, voice assistants, meeting transcriptions, and customer support automation.

2. Production-Ready: Built with comprehensive error handling, follows Strands best practices, supports 30+ languages, and includes real-world examples. Ready to use in production environments.

3. Saves Development Time: Developers can integrate speech processing in minutes instead of spending days building Deepgram integration from scratch.

4. Complete Workflows: Works seamlessly with other community tools (strands-hubspot for CRM lookups, strands-teams for notifications) to create end-to-end workflows like call transcription → customer lookup → team notification.

5. Community Benefit: Open-source with comprehensive documentation and examples. Other developers can learn from it, contribute to it, and build upon it.

[eraykeskinmac]

Closing - using individual .md files per tool instead. See PR #320.