Allo-Media

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.

GitHub

Documentation

📖
Documentation
https://docs.allo-media.net/stream-h2h/
📖
APIReference
https://docs.allo-media.net/stream-h2h/protocol/
📖
GettingStarted
https://docs.allo-media.net/stream-h2h/python/getting-started/
📖
Authentication
https://raw.githubusercontent.com/api-evangelist/allo-media/refs/heads/main/authentication/allo-media-authentication.yml

Other Resources

🔗
WebSocket
wss://api.uh.live/socket/websocket
🔗
JavaScript SDK
https://www.npmjs.com/package/@uhlive/javascript-sdk
🔗
Python SDK
https://pypi.org/project/uhlive/
🔗
ChangeLog
https://docs.allo-media.net/stream-h2h/protocol/releases-notes/

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/allo-media-stream-api-humans"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

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/