ORVIO: Voice Tools

ORVIO is a voice tool for reading short text aloud using a voice you register.

Register a voice Record your own script or import a WAV, M4A or MP3 audio file. Only use your own voice. You can save the recording script with the voice.

Create audio from text Choose a registered voice and speech language, then enter text to create audio. Play, save and share the result. Search your history and keep favorites.

Process on your device The initial setup downloads approximately 884 MB of speech model data. You can record while the download runs. After setup, speech generation runs on your device without sending recordings or entered text to a speech generation service. The model host receives connection information during downloads. Importing a file from cloud storage or sharing audio externally may use a network connection.

Speech languages Japanese, English, Chinese, Korean, German, French, Russian, Portuguese, Spanish and Italian, plus automatic language detection. Language selection does not translate text. The interface supports Japanese and English.

Appearance Light and dark modes follow your device settings, with a manual choice in the app.

Before you start Allow at least approximately 1 GB for the model, plus storage for your audio. ORVIO is designed for short text. Each generation has a length limit and may end before the text is complete. Generation can take several minutes depending on your device and text. Keep the app in the foreground while generating. Voice similarity and pronunciation vary with the recording, text and language.

Review generated audio before using it and label it as synthetic when publishing. Impersonation, fraud and infringement of others' rights are not permitted. No account, advertisements or in-app purchases are required or included.

Speech generation uses a quantized Qwen3-TTS model published by the Qwen team. ORVIO is an independent app, not an official Qwen or Alibaba Cloud app.

Sinais de descoberta