# fossasia/voxbento

Open Source AI powered Interpretation Platform https://voxbento.com

Repository: https://github.com/fossasia/voxbento
Canonical: https://ross.abutalabs.com/products/voxbento
Homepage: https://voxbento.com
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-08-26T13:19:16+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 100
- inputs: {"age_days": 3397, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1482, forks 54 (observed 2026-08-28T04:04:51.143998+00:00)

## What it is
Voxbento is an open-source, self-hosted platform for real-time simultaneous interpretation at live events. Interpreters broadcast translated audio from their browsers via WebRTC/WHIP through MediaMTX to attendees with sub-second latency, with optional AI transcription and LLM-powered translation for captions.

## Use cases
- provide real-time interpretation channels for conference attendees
- run virtual interpreter booths with seamless handoff between interpreters
- add live AI captions and translated subtitles to a livestream
- let attendees listen to a language channel of their choice in the browser
- synchronize translated audio with a delayed video feed
- capture floor audio from Jitsi for automatic transcription and translation

## When to choose
- you host multilingual live events and want a zero-install, browser-based interpretation solution
- you need sub-second audio latency for listeners via WebRTC
- you want self-hosted control over interpretation infrastructure with human interpreters plus AI captions

## When to avoid
- you only need offline or file-based translation rather than live event interpretation
- you cannot run your own MediaMTX/Jitsi/Docker infrastructure
- you need a fully managed SaaS without self-hosting responsibilities

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, websocket, http-server, llm-inference, streaming, self-hosted
- domain: speech-processing, web-development, self-hosted
- platform: python, self-hosted, browser, cross-platform
- tags: simultaneous-interpretation, webrtc, whip, whep, mediamtx, jitsi, live-captions, translation, fastapi, live-events, natural-language-processing, localization, real-time, web-server, docker

## Member repositories
- fossasia/voxbento (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.143998+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 2026-08-30T04:34:07.100682+00:00, confidence not recorded.
  - readme: https://github.com/fossasia/voxbento (fetched 2026-08-28T04:04:51.143998+00:00, sha 57a967a7a8b1)
  - homepage: https://voxbento.com (fetched 2026-08-29T11:40:46.675607+00:00, sha 38c202553aad)
  - site_page: https://docs.voxbento.com (fetched 2026-08-29T11:40:46.678033+00:00, sha 23a5b632663c)
- Data as of 2026-08-30T08:39:29.467469+00:00.