# Self-hosted alternatives to OpenAI Text-to-Speech API

> 1 self-hostable, open-source alternative to OpenAI Text-to-Speech API, ranked by score.

- [kokoro-web](https://selfhost.directory/project/kokoro-web)

## Also in Text to Speech

Not listed as OpenAI Text-to-Speech API alternatives, but from the same category:

- [openai-edge-tts](https://selfhost.directory/project/openai-edge-tts): A self-hosted, open-source text-to-speech API server that mimics OpenAI's /v1/audio/speech endpoint and synthesizes audio for free via Microsoft Edge's TTS voices.
- [chatterbox-tts-api](https://selfhost.directory/project/chatterbox-tts-api): Chatterbox TTS API is a self-hosted, OpenAI-compatible TTS server with voice cloning and 22-language support. Runs via Docker or Python, integrates with Open WebUI.
- [Kokoro FastAPI](https://selfhost.directory/project/kokoro-fastapi): A self-hosted, open-source FastAPI wrapper for the Kokoro-82M speech model with an OpenAI-compatible endpoint, multi-speaker mixing, SSML, timestamps and a web player.
- [OmniVoice-Studio](https://selfhost.directory/project/omnivoice-studio): This self-hosted, open-source ElevenLabs alternative clones and designs voices, dubs video and builds audiobooks in 646 languages, fully local on desktop or Docker.
- [unspeech](https://selfhost.directory/project/unspeech): unSpeech is a self-hosted, open-source TTS proxy with an OpenAI-compatible API for multiple cloud providers like ElevenLabs, Azure, and Deepgram.
- [ebook2audiobook---Legacy](https://selfhost.directory/project/ebook2audiobook-legacy): Self-hosted, open-source converter that turns ebooks and PDFs into audiobooks using multiple TTS engines, voice cloning, OCR and 1158 languages.

All 13 Text to Speech projects: https://selfhost.directory/text-to-speech

---
Source: https://selfhost.directory/alternative-to/openai-text-to-speech-api