# strob/gentle

gentle forced aligner

Repository: https://github.com/strob/gentle
Canonical: https://ross.abutalabs.com/products/gentle
Homepage: https://rmozone.com/gentle/
Language: Python
License: MIT
License Family: permissive
Last push: 2026-07-24T18:57:24+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 8, longevity 100
- inputs: {"age_days": 3967, "days_push": 40, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1705, forks 307 (observed 2026-08-28T04:05:24.832651+00:00)

## What it is
Gentle is a robust yet lenient forced aligner built on Kaldi that aligns audio speech with a known text transcript. It can be used as a Mac GUI app, a Dockerized web server with a REST API, or a Python command-line tool.

## Use cases
- align a transcript with an audio recording word by word
- get word-level timestamps for podcast or video audio
- serve forced alignment over a REST API
- transcribe audio and view alignment results in a browser
- batch-align audio files from the command line

## When to choose
- you need word-level alignment of speech to a known transcript
- you want a self-hosted aligner with a simple REST API
- you prefer a Kaldi-based aligner that tolerates transcript mismatches

## When to avoid
- you need full speech-to-text without a reference transcript
- you need Windows-native support without Docker
- you need actively developed cutting-edge ASR features

## Facets
- artifact type: library
- maturity: maintenance
- function: speech-recognition, nlp, audio-processing, http-server, cli
- domain: speech-processing, media
- platform: python, cli
- tags: forced-alignment, kaldi, transcription-alignment, rest-api, audio-text-alignment, natural-language-processing, audio, macos, linux, docker, web-server

## Member repositories
- strob/gentle (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:24.832651+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 2026-08-30T03:37:33.413380+00:00, confidence not recorded.
  - readme: https://github.com/strob/gentle (fetched 2026-08-28T04:05:24.832651+00:00, sha 43c8663b411b)
  - homepage: https://rmozone.com/gentle/ (fetched 2026-08-29T11:11:49.209505+00:00, sha 4258aa1fb831)
- Data as of 2026-08-30T08:39:29.467469+00:00.