Manage and upgrade your Android voices
Onyx TTS is not a voice pack. It is an Android voice manager and system TTS bridge for:
• Local Piper ONNX voices
• Custom HTTP voice servers
• ElevenLabs voices using your own API key
Onyx makes these voices available to compatible apps through Android’s standard text-to-speech framework.
Upgrade a Piper voice with ElevenLabs
For voices you own or have permission to use, Onyx can create an ElevenLabs counterpart from an installed Piper voice.
Onyx generates about 20 seconds of Piper speech for you to preview. If it sounds correct, you can upload it to ElevenLabs to create the new voice.
The ElevenLabs version keeps the Piper voice’s exact name so Onyx can pair them automatically.
When paired:
• ElevenLabs provides the more expressive online voice
• Piper remains installed as its offline backup
• Onyx returns to Piper if the connection fails, an error occurs, or ElevenLabs responds too slowly
This lets you enhance a familiar Piper voice with the expressiveness and higher potential quality of ElevenLabs without losing offline speech.
Results vary. Cloning synthetic Piper audio may produce lower quality than clean original recordings. An ElevenLabs API key, eligible account, and permission to use the voice are required.
Local, cloud, and self-hosted voices
Piper ONNX
Install compatible Piper ONNX models for fast, private speech generated on your device without an internet connection.
ElevenLabs
Connect ElevenLabs with your own API key. Use your existing voices or create an ElevenLabs counterpart from an eligible Piper voice.
Custom HTTP voices
Connect compatible HTTP TTS endpoints hosted on your local network or online. Use speech models running on your computer, home server, cloud server, or another compatible service.
Use your voices across Android
After setting Onyx as your system TTS engine, your voices can be used by many compatible:
• Accessibility tools and screen readers
• Ebook and document readers
• Communication and productivity tools
• Apps that support Android system TTS
Onyx also supports Tasker through its companion plug-in. Tasker automations can select an Onyx voice to speak text or generate a WAV file using Piper, ElevenLabs, or HTTP voices.
Google Maps is an exception and does not use Onyx for navigation. Other apps with their own speech systems may also ignore Android’s selected TTS engine.
Features
• Manage Piper, ElevenLabs, and HTTP voices
• Clone eligible Piper voices into ElevenLabs counterparts
• Preview reference audio before uploading
• Pair matching ElevenLabs and Piper voices
• Use Piper as an automatic offline fallback
• Connect local or remote HTTP voice servers
• Use self-hosted models through Android system TTS
• Add speech and WAV generation to Tasker automations
• Keep the built-in Lessac fallback for reliable basic speech
Privacy and control
Piper speech is generated locally.
ElevenLabs receives the text it speaks. Creating a voice also uploads the Piper reference after you approve it.
HTTP voices receive text at the server address you configure, whether local or online.
Onyx lets you manage local, cloud, and self-hosted voices while controlling expressiveness, privacy, reliability, and performance.