Getting started
Open NuTTS, add your speech provider API key in Settings, import or create a text document, then open the document detail page and choose Convert Audio.
Supported documents
NuTTS can import plain text, Markdown, Word .docx, and readable PDF files. Scanned PDFs without embedded text are not supported unless they are converted with OCR first.
Speech provider setup
NuTTS is built around Alibaba Cloud Model Studio Qwen-TTS and Qwen-compatible endpoints. API keys are saved in Keychain. You can choose endpoint, model, voice, and background playback in Settings.
Long document generation
Long text is split into segments for synthesis. NuTTS downloads each segment, tracks progress, and can merge the final result into a single local audio file.
Playback and export
Generated audio can be played inside NuTTS and exported when a local audio file is available. If background playback is enabled, audio can continue after locking the device or switching apps.
Troubleshooting
If synthesis fails, check your API key, endpoint, model, voice compatibility, and network connection. If import fails, try a UTF-8 text file or re-export the document as a standard .docx or text-based PDF.