Speaches

OpenAI-compatible speech-to-text and text-to-speech server

Self-Hosted AI ★ 3.7k stars Medium setup MIT

Speaches is a self-hosted server that provides OpenAI-compatible transcription, translation, and text-to-speech endpoints. It supports streaming and a range of open speech models for private voice applications.

Key features

  • OpenAI-compatible audio API
  • Streaming transcription
  • Text-to-speech support
  • Multiple open models

Strengths

  • Released under the MIT license
  • First-class Docker support for quick deployment
  • Active community (3.7k GitHub stars)
  • Written in Python

Is Speaches secure?

OSV.dev has no published security advisories for Speaches's repository. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

Source: OSV.dev, checked 2026-10-14. How this is measured.

Speaches replaces

Health badge

Maintain Speaches? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 82 · excellent

Markdown
[![SelfHostIndex health score for Speaches](https://selfhostindex.com/badge/speaches.svg)](https://selfhostindex.com/app/speaches/)
HTML
<a href="https://selfhostindex.com/app/speaches/"><img src="https://selfhostindex.com/badge/speaches.svg" alt="SelfHostIndex health score for Speaches"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/speaches.svg
   :alt: SelfHostIndex health score for Speaches
   :target: https://selfhostindex.com/app/speaches/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Compare Speaches

8 head-to-head comparisons.

Similar self-hosted ai apps