OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Maise

Maise is an open-source Android speech-engine app that provides on-device text-to-speech and automatic speech recognition through Android system services. Its TTS service uses Open Phonemizer and Kokoro, while recognition transcribes with distil-whisper through Android’s RecognitionService interface.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Maise — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Maise when an Android device or compatible app needs on-device speech synthesis or recognition through the system TTS and SpeechRecognizer interfaces.

Who it is for

  • Android users who want system speech output from apps that use TextToSpeech.
  • Android users seeking speech recognition for apps built on SpeechRecognizer.
  • Android developers who want compatible apps to use system-provided speech services.

Documented uses

  • Read text aloud through Android apps using the standard TTS API.
  • Convert microphone audio to text through apps using the standard speech-recognition API.
  • Choose and preview a bundled voice in Maise’s app.
Before you choose

Requirements & limits

The project is open source under the MIT license. Its README documents building a release APK with Gradle.

  • Both speech workflows are described as running fully on-device using ONNX Runtime.
  • Speech synthesis uses Kokoro voices listed for English, German, French, Greek, Italian, Japanese, Brazilian Portuguese and Simplified Chinese.
  • Recognition uses distil-whisper/distil-small.en, while the voice list includes multiple languages.
  • Recognition requires RECORD_AUDIO permission for the app making the request.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set Maise as Android’s text-to-speech engine

Route speech output from Android apps using TextToSpeech through Maise.

Before you start

  • Maise installed on an Android device.

Steps

  1. Open Settings > Accessibility > Text-to-Speech Output.

  2. Select Maise as the preferred engine.

Expected outcome

Apps using Android’s TextToSpeech API use Maise for speech output.

Guide limitations

  • This configures text-to-speech; recognition requires a separate system setting.
Documentation 1 ↗
Source-based practical guide

Set Maise as Android’s speech recognizer

Route recognition requests from apps using SpeechRecognizer through Maise.

Before you start

  • Maise installed on an Android device.
  • The app using recognition must have RECORD_AUDIO permission.

Steps

  1. Open Settings > Apps > Default Apps > Assist & voice input.

  2. Select Maise as the preferred recognizer.

Expected outcome

Apps using Android’s SpeechRecognizer API can use Maise as the system recognizer.

Guide limitations

  • This configures speech recognition; text-to-speech requires a separate system setting.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
Mobile-Artificial-Intelligence/maise · Official homepage title · retained in its source language
How we review sourcesSuggest a correction