Voice Recognition

Orpheus-FastAPI – high-performance self-hosted text-to-speech server

Orpheus-FastAPI is a high-performance self-hosted text-to-speech server built with FastAPI.

It provides an OpenAI-compatible /v1/audio/speech endpoint together with a modern web interface for generating speech locally. The project is designed to work with external inference servers such as llama.cpp, LM Studio, and GPUStack, and focuses on fast GPU-accelerated synthesis with support for expressive tags, long-form generation, and multilingual voice models.

This is free and open source software.

Key Features

  • Provides an OpenAI-compatible text-to-speech API endpoint.
  • Includes a responsive web interface with waveform visualisation.
  • Supports multilingual speech synthesis with multiple voices across several languages.
  • Supports emotion tags for more expressive generated speech.
  • Handles long-form audio generation through batching and crossfaded stitching.
  • Can connect to external inference servers such as llama.cpp, LM Studio, and GPUStack.
  • Offers Docker deployment options for GPU, ROCm, and CPU-based setups.
  • Optimised for fast local inference on RTX-class GPUs.

Website: github.com/Lex-au/Orpheus-FastAPI
Support:
Developer: Alexander J.
License: Apache License 2.0

Orpheus-FastAPI is written in Python. Learn Python with our recommended free books and free tutorials.


Related Software

Speech Tools
PiperFast, local neural text to speech system
TortoiseMulti-voice text-to-speech system trained with an emphasis on quality
Coqui TTSOffers pretrained models in more than 1,100 different languages
BarkTransformer-based text-to-audio model.
FestivalGeneral multi-lingual speech synthesis system
PraatSpeechAnalyserSoftware for speech analysis and synthesis
Speech NoteSpeech to Text, Text to Speech and Machine Translation
Mimic 3Lightweight Text to Speech engine
OrcaScreenReaderScriptable screen reader
FliteSmall, fast run time text to speech synthesis engine
RHVoiceGives the visually impaired a synthesis voice with their screen reader
eSpeak NGContinuation of the eSpeak project
eSpeakSpeech synthesizer using a formant synthesis method
GespeakerGTK-based frontend for eSpeak

Read our verdict in the software roundup.


Best Free and Open Source Software Explore our comprehensive directory of recommended free and open source software. Our carefully curated collection spans every major software category.

This directory is part of our ongoing series of informative articles for Linux enthusiasts. It features hundreds of detailed reviews, along with open source alternatives to proprietary solutions from major corporations such as Google, Microsoft, Apple, Adobe, IBM, Cisco, Oracle, and Autodesk.

You’ll also find interesting projects to try, hardware coverage, free programming books and tutorials, and much more.

Discovered a useful open source Linux program that we haven’t covered yet? Let us know by completing this form.
Subscribe
Notify of
guest
0 Comments
Oldest
Newest Most Voted
Inline Feedbacks
View all comments