Examples and their prompts
Results from this generator. A prompt can be used as it is, or copied and edited.
Available audio models
Every model shows only the settings it supports. Select a model in the box above; switching models keeps the prompt.
Model list updated
How to generate audio
Three steps from text to finished speech.
Choose a voice model
Choose a speech model.
Enter the text
Write or paste the text to speak.
Generate and save
Set the options the model offers, check the price, and click Generate.
Using a voice in a video
Pictures are made in the image generator and the voice here. The free MP3 to Video tool then combines the voice and the pictures into an MP4.
- Create a picture
- Generate the voice
- Combine them
Frequently asked questions
Answers to frequently asked questions.
Can it make songs or music?
No. The AI audio generator makes speech. For music or effects in a clip, use a video model with sound in the AI Video Generator.
Can I trim the result?
Yes. The free Audio trim tool runs in the browser: open the file, select the range and export in the required format.
Which formats can I download?
The format options depend on the model. The Audio trim tool can also convert a file to WAV, MP3, M4A, AAC, OGG, FLAC or WebM.
Can I choose a different voice?
Not yet. Every take uses the same built-in voice; the model's settings change its speed and delivery.
Need more information? Email us at support@arumi.ai.
Start generating
Create images, video, audio and music from a text description with Arumi.