A description becomes a voice
Guide delivery with everyday language instead of reference audio.
MOSS Voice Generator
MOSS Voice Generator: Design an AI Voice from Text
Describe a voice and hear it speak with MOSS Voice Generator. Explore tone, emotion and delivery for a new narration or creative character.
8 credits / 1,000 charactersYour credits work across all models.
Your output
A little input. A new possibility.
Your finished audio, image or text will appear here.
01 / Inside the model
Describe the voice you have in mind.
MOSS VoiceGenerator designs a speaking voice from a natural-language description. Rather than finding a reference recording, describe the vocal character you want and supply the words to speak. The official model demonstrates Chinese and English speech with varied texture, age, accent and emotion. In this workspace, a voice description and a script form a single generation request. Start with a concise description and refine one quality at a time.
Character and texture
Describe a warm, bright, rough or restrained vocal quality.
Words and delivery together
Provide both the voice direction and the text to be spoken.
02 / Examples & listening room
Explore the official modelSee it. Hear it. Get a feel for it.
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.
Warm documentary narration
Studio sample · English03 / Use cases
Where it fits.
Character exploration
Try an original fictional character voice for a creative draft.
Brand narration
Explore a consistent tone for a guide, explainer or product introduction.
04 / Questions
A few things worth knowing.
Do I need a reference recording?
No. This workflow uses a written voice description and spoken text.
What does voice design cost?
8 credits per 1,000 spoken input characters, rounded up with a one-credit minimum. The separate voice direction is not billed as spoken text.
Can I save the voice as a preset?
A reusable voice-profile library is not available here. Keep your description and download your audio result.
Made for your next idea
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.
Failed tasks are refunded automatically.
Result links can expire. Download files you want to keep.
Model documentation