Drop-in OpenAI TTS-compatible server. Self-hosted, talks to local voice models.
Editorial verdict: “Best 'drop-in local TTS for OpenAI clients'. Bridge solution for existing pipelines.”
Which runtime + OS combos this app works against. Source of truth for "will it run on my setup?"
For teams already wired to OpenAI’s TTS API, OpenedAI-Speech is the most direct path to fully offline voice synthesis. It accepts the same request format as OpenAI’s `/v1/audio/speech` endpoint, then routes to local models like Piper (fast, low-footprint) or Coqui XTTS-v2 (higher quality, needs ~4 GB VRAM). Setup requires Docker Compose and manual model path configuration, so it’s not a one-click install. Once running, any client that speaks OpenAI TTS—Home Assistant, custom chatbots, automation scripts—works without code changes. The AGPL-3.0 license is fine for personal use, but teams building proprietary products should check compatibility.
Transcription, speech-to-text, or text-to-speech.
Pre-filled with this app's recommended use case + budget tier. Get the full rig + runtime + model picks.
The full directory — filter by category, runtime, OS, privacy posture, or VRAM.
What this app talks to: Ollama, vLLM, llama.cpp, MLX, LM Studio. The upstream layer.
Did this app work for you on a specific rig? Submit the benchmark — it powers the model + hardware pages.