revdotcom/revai-python-sdk

Provides both asynchronous job-based transcription (supporting file uploads and URLs) and real-time streaming audio via WebSocket, with support for AI-powered features like summarization, multi-language translation, speaker diarization, and human transcription services. Outputs transcripts in multiple formats (text, JSON, SRT/VTT captions) with optional streaming delivery, and supports configurable deployments across different Rev AI infrastructure regions. Advanced options include custom vocabularies, profanity filtering, and selective segment transcription for human transcribers.