Speech & translation

Transcription, text-to-speech and machine translation you can run in-house.

Quick answer

We track 2 self-hostable speech & translation apps: LibreTranslate, Speaches. Most GitHub stars: LibreTranslate (17.1k). None of them publishes an official CPU/RAM figure we could use for a server-cost estimate.

Last updated

Speech & translation: side-by-side

AppLicenseOfficial hardwareEst. server costGitHub starsStatus
LibreTranslateAGPL-3.0 (Network copyleft (AGPL))Not publishedNot estimated (no official RAM figure)17.1kActive
SpeachesMIT (Permissive)Not publishedNot estimated (no official RAM figure)3.7kStale (no commit in 180+ days)

All speech & translation apps

Self-hosted machine translation API with no dependency on Google or DeepL.

  • ★ 17.1k
  • ⟳ Oct 12, 2026
  • Network copyleft (AGPL)
  • RAM: n/a
  • Cost: n/a

Speaches

Stale

OpenAI-compatible speech-to-text and text-to-speech server (faster-whisper, Kokoro, Piper).

  • ★ 3.7k
  • ⟳ Apr 18, 2026
  • Permissive
  • RAM: n/a
  • Cost: n/a