Skip to content
store
Speechbrain

Self-hosted alternatives to Speechbrain

50 self-hosted Music apps to use instead, best rated first.

Top picks

  1. A

    Audiobookshelf

    Launch

    Audiobookshelf is a self-hosted server that allows you to manage and stream your audiobook and podcast collection from anywhere. It provides a robust and user-friendly interface to organize, stream, and enjoy your audio content seamlessly a

    Self-hosted

  2. A

    Amberol

    Launch

    A RAD tool to enable quick & easy development of user interfaces for the GTK toolkit and the GNOME desktop environment. Note that as of January 9, 2026, the recentmost Windows version (3.14.2) lags noticeably behind the recentmost Linux ver

    Self-hosted

  3. L

    Lidarr

    Launch

    **Lidarr is a music collection manager for Usenet and BitTorrent users.** It can monitor multiple RSS feeds for new tracks from your favorite artists and will grab, sort and rename them. It can also be configured to automatically upgrade th

    Self-hosted

  4. M

    Mopidy

    Launch

    Mopidy is an extensible music server written in Python. It plays music from local disk, from Spotify, SoundCloud and internet radio, and it offers a superset of the MPD API, so the playlist can be edited from any phone, tablet or computer u

    Self-hosted

  5. B

    Black Candy

    Launch

    A self hosted music streaming server

    Self-hosted

  6. S

    Snapcast

    Launch

    Snapcast is a synchronous multiroom audio server and client. It is not a standalone player. It is an extension that turns your existing audio player into a multiroom system, which the README compares to a Sonos-like setup. The server captur

    Self-hosted

More Music apps

See all
7
M

mStream

Music streaming server with GUI management tools

Launch
8
P

Pinepods

Podcast management system with multi-user support

Launch
9
F

Feishin

A modern self-hosted music player

Launch
10
T

Tdarr

Distributed transcode automation

Launch
11
M

musikcube

Streaming audio server with Linux/macOS/Windows/Android clients

Launch
12
D

Downtify

Download Spotify music with album art and metadata. (Source Code) GPL-3.0 Docker

Launch
13
P

Polaris

Music browsing and streaming application optimized for large music collections

Launch
14
G

gonic

Lightweight music streaming server. Subsonic compatible

Launch
15
O

OpenReader

EPUB, PDF, DOCX, MD, and TXT file text to speech document reader

Launch
16
S

Swingmusic

Swing Music is a beautiful, self-hosted music player for your local audio files

Launch
17
P

Podsync

Turn YouTube or Vimeo channels, users, or playlists into podcast feeds

Launch
18
M

mpd

Daemon to remotely play music, stream music, handle and organize playlists

Launch
19
S

slskd

Web app for the Soulseek file-sharing network

Launch
20
M

Maloja

Self-hosted music scrobble database to create personal listening statistics

Launch
21
N

NeriPlayer

A native Android audio player that combines multi-source streaming, local…

Launch
22
M

moOde Audio

Audiophile-quality music playback

Launch
23
E

Explo

Spotify's "Discover Weekly" for self-hosted music systems

Launch
24
M

Multi Scrobbler

Scrobble plays from multiple sources to multiple clients

Launch
25
P

PigeonPod

Listen to YouTube & Bilibili. Anywhere

Launch
26
L

LMS

Lightweight Music Server. Access your self-hosted music using a web interface

Launch
27
S

Supersonic

A lightweight and full-featured cross-platform desktop client

Launch
28
K

Koito

Koito is a modern, themeable scrobbler that you can use with any program

Launch
29
S

SoulSync

Automated music discovery and collection manager

Launch
30
I

I Don't Have Spotify

Effortlessly convert music links between streaming services

Launch
31
A

Aurral

Streamlined artists requests for Lidarr

Launch
32
J

JellyBoxPlayer

A native desktop and mobile music player for Jellyfin and Emby

Launch
33
M

Metadata Remote

Edit metadata on headless servers (or anywhere else) via a clean web…

Launch
34
T

Tempo

An open source and lightweight music client for Subsonic

Launch
35
D

DroppedNeedle

Music request and discovery for Lidarr

Launch
36
P

Podgrab

A self-hosted podcast manager/downloader/archiver tool

Launch
37
V

Vocard

Vocard is a simple music bot

Launch
38
M

Muse

a self-hosted midwestern Discord music bot that doesn't suck

Launch
39
A

Audioserve

Simple personal server to serve audio files from directories

Launch
40
J

JcorpNomad

An extremely compact offline media server for Movies, Shows, Books, and Music

Launch
41
L

LMS

Access your self-hosted music using a web interface

Launch
42
P

PodFetch

A sleek and efficient podcast downloader

Launch
43
S

Stretto

Music player with Youtube/Soundcloud import and iTunes/Spotify discovery

Launch
44
T

Tempus

An open source and lightweight music client for Subsonic

Launch
45
O

Openclaw Nerve

Real-time web cockpit for OpenClaw: voice conversations

Launch
46
I

Its Mytabs

Open source, web based, self hostable guitar/bass tab

Launch
47
J

Jellyfin Rewind

Review Your Music of 2025

Launch
48
C

Cicada

A multi-user music service for self-hosting

Launch
49
M

Mobile App

The (official) Music Assistant Mobile app is a cross-platform client application

Launch
50
O

Octo-Fiesta

Subsonic proxy for integrating streaming providers as music sources

Launch

About Speechbrain

S

Speechbrain

A PyTorch-based Speech Toolkit

SpeechBrain is an open-source PyTorch toolkit for building conversational AI, the technology behind speech assistants, chatbots and large language models. It is designed for fast, straightforward creation of speech and text processing systems, and its scope covers speech recognition, speaker recognition, speech enhancement, speech separation, language modelling and dialogue. The project shares more than 200 training recipes across more than 40 datasets, covering 20 speech and text processing tasks. You can train from scratch or fine-tune pretrained models such as Whisper, Wav2Vec2, WavLM, HuBERT, GPT-2 and Llama 2, and models on Hugging Face can be plugged in and fine-tuned. For each task, the hyperparameters live in a YAML file and a Python script orchestrates the training, and the code structure is kept consistent across tasks. Training logs and checkpoints for replication are hosted externally. Over 100 pretrained models are available on Hugging Face, and each comes with an interface for inference, so transcription with a pretrained model takes a few lines of code. The project has written more than 30 tutorials, and every class and function has examples that can be run. Recent releases added support for the EEG modality, which the authors describe as part of their goal of natural conversation between people and machines. The project is on GitHub, with a website, tutorials, a Hugging Face organisation and a YouTube channel.

View SpeechbrainAll Music apps
Price
Free
Made by
speechbrain
Category
Music
Website
github.com/speechbrain/speechbrain