Self Host An Openai Compatible Speech Api For Local Transcription Translation And Tts With Speaches

---
name: "Self-host an OpenAI-compatible speech API for local transcription, translation, and TTS with Speaches"
slug: "self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches"
description: "Use Speaches when an agent stack expects OpenAI-style audio endpoints but you want a self-hosted speech backend for transcription, translation, and text-to-speech instead of a hosted API."
github_stars: 3170
verification: "security_reviewed"
source: "https://github.com/speaches-ai/speaches"
author: "speaches-ai"
publisher_type: "company"
category: "Media & Transcription"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "speaches-ai/speaches"
  github_stars: 3170
---

# Self-host an OpenAI-compatible speech API for local transcription, translation, and TTS with Speaches

Use Speaches when an agent stack expects OpenAI-style audio endpoints but you want a self-hosted speech backend for transcription, translation, and text-to-speech instead of a hosted API.

## Prerequisites

Docker or Python-based deployment environment, CPU or GPU runtime, supported speech models, and any client or agent stack that can call OpenAI-compatible audio endpoints.

## Installation

Requirements and caveats from upstream:
- [Deployable via Docker Compose / Docker](https://speaches.ai/installation/)

Basic usage or getting-started notes:
- See the documentation for installation instructions and usage: [speaches.ai](https://speaches.ai/)
- [Realtime API](https://speaches.ai/usage/realtime-api)

- Source: https://github.com/speaches-ai/speaches
- Extracted from upstream docs: https://raw.githubusercontent.com/speaches-ai/speaches/HEAD/README.md

## Documentation

- https://speaches.ai

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/self-host-an-openai-compatible-speech-api-for-local-transcription-translation-and-tts-with-speaches/)