OpenedAI Speech logo
AI · self-hosted

OpenedAI Speech in one click.

OpenedAI Speech is an openai-compatible tts api using kokoro and piper you can run on your own machine. Launch it in Even Stacks in one click, serve it over trusted HTTPS, and let your AI agents operate it.

What is OpenedAI Speech?

Self-hosted OpenAI-compatible text-to-speech API server using Kokoro and Piper TTS engines, supporting multiple voices and WAV, MP3, and Opus output formats.

CategoryAI
Default port8818
Container imageghcr.io/matatonic/openedai-speech:latest

Run OpenedAI Speech in Even

Even Stacks launches OpenedAI Speech as a managed container on your own machine. No compose files, no manual setup.

  1. Open the Even Stacks panel in Even. The container engine starts on demand.
  2. Find OpenedAI Speech in the one-click services and click Launch.
  3. Even pulls the image, starts it on port 8818, and serves it over trusted HTTPS at https://openedai-speech.localhost.

Drive OpenedAI Speech with your AI agents

Even ships an MCP, so any agent you run inside Even (Claude Code, Codex, and more) can operate OpenedAI Speech directly, at both the UI level and the container level.

Through the Even MCP an agent can pull a model, call the local endpoint, and wire it into a tool, all on your own hardware. It runs commands inside the container, reads its logs, and for web apps opens and clicks through the interface in Even's own browser pane. Ask once, for example "set up OpenedAI Speech and get it ready", and the agent handles it end to end.

How agents reach it: REST API compatible with OpenAI TTS; POST to http://localhost:8818/v1/audio/speech with JSON body {model, input, voice} to receive audio. No web UI; manage voice models by placing files in the mounted /app/voices and /app/models volumes.

More AI services

Other one-click services you can launch in Even Stacks.