PodWarden Cloud
CatalogCase StudiesNewsDocsGitHubEarly Adopter

PodWarden — Fleet operations as a product

CatalogNewsDocumentationGitHubEarly Adopter|Terms of ServicePrivacy PolicyAcceptable Use
CatalogAI / Machine LearningOpenedAI Speech

OpenedAI Speech

matatonic

Learn how to self-host
Install with PodWardenLearn how to deploy with PodWarden

OpenAI-compatible text-to-speech API server using Piper and XTTS v2 backends, with voice cloning and multiple output formats.

AI / Machine LearningMediaFree
#xtts#openai-compatible#voice-cloning#piper#tts#api#text-to-speech
Learn how to self-host
Learn how to deploy with PodWarden

About

OpenedAI Speech is a drop-in replacement for OpenAI's TTS API endpoint (/v1/audio/speech). It uses Piper (fast, CPU-friendly) and XTTS v2 (high-quality, GPU-accelerated) as backends, supporting voice cloning and multiple audio formats.

Deployment Options

2 stacks

You might also like

Coqui TTS

AI / Machine Learning

Kokoro TTS

AI / Machine Learning

Speaches

AI / Machine Learning

Piper

Piper

AI / Machine Learning

F5-TTS

AI / Machine Learning

XTTS

AI / Machine Learning

Requirements

1000m
4Gi
GPU 1x
8000

Stacks

Full (Piper + XTTS)Service
Minimal (Piper only)Service

Author

matatonic

Project page

Tags

#xtts#openai-compatible#voice-cloning#piper#tts#api#text-to-speech
How to deploy with PodWardenSelf-hosting guide