ai_provider_assemblyai

Looking for industry-leading speech-to-text capabilities? AssemblyAI delivers state-of-the-art speech recognition powered by advanced AI models. Integrated with the AI module, AssemblyAI Provider brings professional-grade audio transcription, speaker identification, and content analysis directly to your Drupal site.

Features

Transform audio into actionable content with AssemblyAI powerful features:

• Universal-3-Pro: Highest accuracy speech recognition across 6 languages with advanced prompting capabilities
• Universal-2: Fast, accurate transcription supporting 99+ languages with automatic language detection
• Speaker Diarization: Automatically identify and separate different speakers in your audio
• Content Intelligence: Extract chapters, detect entities, analyze sentiment, and identify key highlights
• PII Redaction: Automatically detect and remove sensitive information (credit cards, SSNs, emails, phone numbers)
• Custom Vocabulary: Boost accuracy for industry-specific terms, product names, and technical jargon
• Content Safety Detection: Identify and flag sensitive content categories
• Real-time Processing: Webhook support for asynchronous transcription workflows

Leverage these models through the full range of the AI module family to enhance content creation, accessibility, and media management workflows.

Post-Installation

1. Configure an API key using the Key module with your AssemblyAI API credentials (get yours at assemblyai.com)
2. Navigate to /admin/config/ai/assemblyai and connect your API key
3. Test your connection using the built-in connection tester
4. Configure default settings for transcription (language, speaker labels, formatting, etc.)
5. Start transcribing audio files through the AI module interface or programmatically via the AssemblyAI Provider

Use Cases

• Podcast Transcription: Automatically transcribe episodes with speaker identification for show notes and accessibility
• Meeting Documentation: Convert recorded meetings into searchable, timestamped transcripts with speaker labels
• Content Accessibility: Make audio content accessible with accurate transcriptions and captions
• Customer Service: Transcribe support calls with PII redaction for quality assurance and compliance
• Media Archives: Process large audio archives with batch transcription capabilities
• Educational Content: Transcribe lectures and courses with chapter generation and highlight extraction
• Legal & Medical: Professional-grade accuracy with custom vocabulary support for specialized terminology

Additional Requirements

• The AI module
• AssemblyAI API key (free tier available at assemblyai.com)