# google/live-transcribe-speech-engine

Live Transcribe is an Android application that provides real-time captioning for people who are deaf or hard of hearing. This repository contains the Android client libraries for communicating with Google's Cloud Speech API that are used in Live Transcribe.

Repository: https://github.com/google/live-transcribe-speech-engine
Canonical: https://ross.abutalabs.com/products/live-transcribe-speech-engine
Language: Java
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2022-07-20T03:44:43+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2582, "days_push": 1505, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1499, forks 220 (observed 2026-08-28T04:04:54.079237+00:00)

## What it is
Android client libraries from Google's Live Transcribe app for streaming real-time speech recognition via the Google Cloud Speech API. It provides robust infinite streaming ASR with reconnection handling, audio encoding options, and text formatting for confidence and speaker labels.

## Use cases
- add real-time captioning to an Android app
- stream microphone audio to Google Cloud Speech-to-Text
- build accessibility tools for deaf or hard-of-hearing users
- transcribe live conversations on Android
- handle network interruptions during long speech recognition sessions
- visualize ASR confidence and speaker labels in captions

## When to choose
- you need production-tested Android ASR streaming libraries
- your app must survive brief or extended network loss during transcription
- you want to build real-time captioning features on Android
- you need support for 70+ languages via Cloud Speech API

## When to avoid
- you need offline speech recognition out of the box
- you target iOS or non-Android platforms
- you want a fully self-contained ASR engine without Google Cloud dependency
- you need an actively developed project (last release 2022)

## Facets
- artifact type: library
- maturity: maintenance
- function: speech-recognition, audio-processing, sdk, streaming
- domain: speech-processing, accessibility, mobile-development, android-tools
- platform: jvm
- tags: live-captioning, asr, cloud-speech-api, deaf-and-hard-of-hearing, real-time-transcription, android, mobile

## Member repositories
- google/live-transcribe-speech-engine (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:54.079237+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:33:02.831920+00:00, confidence not recorded.
  - readme: https://github.com/google/live-transcribe-speech-engine (fetched 2026-08-28T04:04:54.079237+00:00, sha 03d8c5319026)
- Data as of 2026-08-30T08:39:29.467469+00:00.