OpenedAI-Speech

Fully offline

Drop-in OpenAI TTS-compatible server. Self-hosted, talks to local voice models.

Editorial verdict: “Drop-in local TTS for OpenAI clients, but archived: the maker calls it mostly obsolete.”

Voice / transcription
Free
AGPL-3.0
★ 4.2 / 5
GitHub ★ 857

Compatibility at a glance

Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"

§ Runtimes supported
openai-compat
§ OS / platform
linuxmacoswindows
§ Hardware + model hint
Minimum VRAM
4 GB
Recommended starter model
Piper voices or Coqui XTTS-v2

What it is

OpenedAI-Speech mimics OpenAI's TTS API endpoint, but routes to local voice models (Piper, XTTS). Drop a config, point any OpenAI-TTS client at it, get local voice synthesis. Pairs well with assistants that already support OpenAI TTS — drop-in replacement. The maker now calls the software mostly obsolete and no longer updates it, and the GitHub repo is archived.

✓ Strengths

  • +True drop-in for OpenAI TTS API
  • +Multiple voice backends (Piper fast, XTTS quality)
  • +Docker Compose setup is documented

△ Caveats

  • −Setup leans technical (docker-compose, model paths)
  • −Smaller user community than Whisper-side tooling
  • −Archived; the maker says it is mostly obsolete and will no longer be updated

About the Voice / transcription category