Script to speech
Generate an audio recording directly from your text.
Turn scripts into natural speech with MOSS TTS Flash. Choose a voice and generate audio for videos, narration and everyday content.
Your finished audio, image or text will appear here.
Turn a written script into speech with the MOSS TTS Flash API model. The wider MOSS-TTS family covers multilingual synthesis, expressive delivery and long-form audio. This workspace keeps the essentials close: enter text, choose a preset voice and generate a downloadable recording. Flash has the lower text-to-speech credit rate here, making it a practical starting point for short scripts and repeated edits.
Generate an audio recording directly from your text.
Compare the preset voices while keeping your script unchanged.
Review the character-based cost before each generation.
Official examples are credited to OpenMOSS. Studio samples were generated by us with the named API model. These are saved previews, not a result of your current settings. Research capabilities and available studio controls may differ.
Try different openings for a walkthrough or a short presentation.
Create spoken versions of lesson notes and short instructional scripts.
4 credits per 1,000 input characters, rounded up to a whole credit with a minimum of one. A 250-character script costs 1 credit.
No. These saved studio previews were generated with the API model named on each card. Your result depends on your text, the model version and your selected preset.
Compare the same short script in both models and choose the output you prefer. Pro uses a different API version and costs 6 credits per 1,000 characters.
Choose a model, add your input and review the credit cost. Successful results stay in your account history; AI output may be inaccurate.
Text is rounded up to a whole credit. Audio is billed per started minute. Live voice uses one credit per 6 seconds.
Result links can expire. Download files you want to keep.
Model documentation