Allo-Media Stream API for Humans

Real-time transcription of live human-to-human conversations over a WebSocket (Phoenix Channels). A client joins a conversation, streams binary audio chunks, and receives interim and final decoded segments plus speaker join and leave events, named entities and analytics tags. Protocol V2 is current, V1 is deprecated. Bandwidth is capped at 20 kB/second per connection.

API entry from apis.yml

apis.yml Raw ↑
aid: allo-media-stream-api-humans
name: Allo-Media Stream API for Humans
description: Real-time transcription of live human-to-human conversations over a WebSocket (Phoenix Channels).
  A client joins a conversation, streams binary audio chunks, and receives interim and final decoded segments
  plus speaker join and leave events, named entities and analytics tags. Protocol V2 is current, V1 is
  deprecated. Bandwidth is capped at 20 kB/second per connection.
humanURL: https://docs.allo-media.net/stream-h2h/
baseURL: https://api.uh.live
tags:
- Speech Recognition
- Streaming
- WebSocket
- Real-Time
tags_raw:
- Speech Recognition
- Streaming
- WebSocket
- Real Time
properties:
- type: Documentation
  url: https://docs.allo-media.net/stream-h2h/
- type: APIReference
  url: https://docs.allo-media.net/stream-h2h/protocol/
- type: GettingStarted
  url: https://docs.allo-media.net/stream-h2h/python/getting-started/
- type: WebSocket
  url: wss://api.uh.live/socket/websocket
- type: Authentication
  url: authentication/allo-media-authentication.yml
- type: JavaScript SDK
  url: https://www.npmjs.com/package/@uhlive/javascript-sdk
- type: Python SDK
  url: https://pypi.org/project/uhlive/
- type: ChangeLog
  url: https://docs.allo-media.net/stream-h2h/protocol/releases-notes/