Kitta AI Docs
Integration GuidesThird-Party Integrations

Android Custom TTS Setup Guide

Connect Custom TTS Service for Android to Kitta AI and use a cloned voice in apps that support the Android system TTS engine.

Use Kitta AI as an Android system TTS engine

Custom TTS Service for Android connects an OpenAI-compatible speech endpoint to Android's system text-to-speech interface. Apps that use the selected Android TTS engine can then read text with a Kitta AI voice.

System TTS boundary

This works only in Android apps that use the operating system TTS engine. An app with its own built-in speech provider may ignore the Android system selection.

Prepare the API key and Voice ID

  1. Create a dedicated key in API management.
  2. Copy your cloned voice's Voice ID.
  3. Confirm that your API credit balance is sufficient.

Use this system voice for the first test:

00a1b221-6137-4b73-ad62-b0cbce134167

Install and configure the engine

Install the APK from the project's release page, open the app, and enter:

SettingValue
Backend URLhttps://kittaai.com/v1/audio/speech
API KeyYour Kitta AI API key
TTS Modelfishaudio-s21pro-flash
TTS Voice00a1b221-6137-4b73-ad62-b0cbce134167
Response Formatwav

Use the complete endpoint and WAV

The Android service posts directly to Backend URL, so include /audio/speech. Its current release supports WAV and PCM playback but does not yet decode MP3 or Opus; use wav for Kitta AI.

Tap Save, then tap Open Android TTS Settings and select Custom TTS as the preferred engine. Use Android's sample playback or an app's read-aloud button to test a short sentence.

Security and voice notes

  • The API key is stored on the Android device. Use a dedicated key that can be revoked without affecting other integrations.
  • The Voice field requires a Kitta AI Voice ID, not the voice's display name.
  • Replace the system test voice with your cloned voice only after the first test succeeds.
  • Network access is required whenever Android asks the engine to synthesize speech.

Troubleshooting

  • No audio: set Response Format to wav; MP3 and Opus are listed but are not decoded by the current app.
  • 404: Backend URL must be the complete https://kittaai.com/v1/audio/speech address.
  • 401: replace the saved API key with a valid dedicated key.
  • 402: add API credits before trying again.
  • 400 or invalid voice: use fishaudio-s21pro-flash and a valid Kitta AI Voice ID.
  • Another voice plays: select Custom TTS in Android's system TTS settings and check whether the target app uses system TTS.