Name: Aloud – Obsidian Plugin · Obsidian Stats
Rating: 61 (106 reviews)
Author: Adrian Lyjak

by Adrian Lyjak

Score: 61/100

Install Code

Description

Category: Note Enhancements

#text-to-speech #openai #audio-playback

The Aloud plugin for Obsidian enhances the note-taking experience by adding text-to-speech functionality. By integrating with OpenAI's API, it converts highlighted text into lifelike audio, offering a range of voices for playback. Features include immediate audio streaming, sentence-by-sentence playback, and customizable speed adjustments. The plugin also allows for audio caching to reduce costs, exporting, and embedding audio files. It provides visual feedback by highlighting the active sentence and integrates seamlessly with your operating system, offering pause/play controls. This plugin is a great tool for those who prefer listening to their notes, whether for accessibility, multitasking, or enhancing focus.

Reviews

Liz Barrett
Reviewed on Apr 8th, 2026
Very easy set up and great quality basic text to speech tool. Simple to set up, simple to use, works exactly as it should.

Stats

stars

16,036

downloads

forks

809

days

total PRs

open PRs

closed PRs

merged PRs

total issues

open issues

closed issues

commits

Latest Version

0.15.0

a day ago

Changelog

What's Changed

Other Changes

Add PCM response format for OpenAI-compatible TTS by @pajaroamarillo in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/144
feat: add MiniMax speech 2.8 models by @adrianlyjak in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/148
Add Ko-fi funding link by @adrianlyjak in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/149
Add Fish Audio TTS provider by @RONNYKHALIL in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/142
Add generation speed setting for OpenAI-compatible TTS by @pajaroamarillo in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/143

New Contributors

@pajaroamarillo made their first contribution in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/144
@RONNYKHALIL made their first contribution in https://github.com/adrianlyjak/obsidian-aloud-tts/pull/142

Full Changelog: https://github.com/adrianlyjak/obsidian-aloud-tts/compare/0.14.5...0.15.0

See all version on GitHub

README file from

Github

Aloud Text To Speech Obsidian Plugin

Highlight and speak text from your Obsidian notes. Converts text to audio using lifelike voices from various providers.

Just add your API key from a supported provider. Choose from available voices.

Supported TTS Models:

OpenAI: (e.g., tts-1, tts-1-hd, gpt-4o-mini). OpenAI charges Audio at $0.015 per 1,000 characters.
Google Gemini: (Gemini 2.5 series)
Hume AI: (Hume voices with customization)
ElevenLabs: (Model selection, voice selection, stability/similarity options)
Fish Audio: (S2 Pro/S1 models with custom voice model IDs)
Azure Speech Services: (Region, voice and output format selection)
MiniMax: (speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo)
AWS Polly: (Region, voice, neural/standard engine, output format)

You can also configure a custom API endpoint if you have an OpenAI compatible API server that has an /v1/audio/speech endpoint. For example openedai-speech.

Features:

Visual Feedback: Active sentence is highlighted and updated as playback progresses.

Listen immediately: Audio is streamed sentence-by-sentence. Jump back and forth by skipping by sentence.

Variable Speeds: On device playback rate adjustor for improved audio quality.

Caching: Audio is cached in your vault to reduce costs, and automatically removed. Cache duration is configurable. Audio may be cached device local or in a vault directory.

Export and Embed Audio: Quickly export to audio files: export audio files from selection, or embed audio by pasting text from your clipboard.

Play text from anywhere: Lots of commands. Play text to speech directly from your clipboard.

OS Integration: Integrates with your mobile phone to play while locked. Pause/Play with OS controls on desktop.

Alternate TTS Models

You can also run alternate models if you have an OpenAI‑compatible API server that exposes /v1/audio/speech (for example, openedai-speech). Configure the URL and API key in the plugin settings under “OpenAI Compatible (Advanced)”.