GetRun / Audio
Generate AI Audio, Priced in Rupiah
Four different audio needs live in one GetRun catalog: turning text into speech, writing songs, making sound effects, and changing the voice on an existing recording. All of them are paid from a rupiah balance as you use them, with the price shown before anything runs. The billing unit follows the shape of the work rather than being flattened into one: text to speech is counted per character read aloud, music and sound effects per second of audio produced, while the song writer is billed per run and returns two versions to choose between.
There are currently 6 audio models from 2 providers, with sample runs starting at Rp123 each.
Why through GetRun
- Text to speech, music, sound effects, and voice changing in one account and one API.
- Models from providers directly — ElevenLabs and Suno — not only through intermediaries.
- Rupiah pricing appears before anything runs; failed generations are never charged.
- Input audio is uploaded through POST /v1/uploads, up to 25 MB.
- The billing unit follows the work: per character for text to speech, per second for music, sound effects, and voice changing.
- Output is MP3 (audio/mpeg), ready to drop into a video editor, a web player, or a mobile app without conversion.
- Audio models are called the same way as image and video models — POST /v1/tasks then polling — so one integration covers the whole catalog.
How to use it
- Decide the kind of audio — Choose between text to speech, music, sound effects, or voice changing in the audio category.
- Fill in the input — Text to speech needs only the text and a voice; voice changing needs an uploaded recording.
- Run it and download — Create the task, poll until it succeeds, then download the MP3 from the result URL within 7 days.
Available audio models
Frequently asked questions
- Which text to speech models are available?
- ElevenLabs text to speech is available directly, billed per character of text read aloud, with the price shown before it runs.
- Can it write a full song with vocals?
- Yes. Suno writes complete songs with vocals and returns two versions per run, billed once per run so you can pick between them.
- How do I change the voice on an existing recording?
- Upload the recording through POST /v1/uploads (up to 25 MB), then pass the returned URL to the voice changer model. Billing is per second of audio.
- How long can I download the resulting audio file?
- Output URLs expire after 7 days. Copy the file to your own storage if you need it longer.
- How do I work out a voice over cost before running it?
- Text to speech is billed per character, so the cost follows the length of your script. The estimate appears on the confirmation screen before the task is created.
- What file format comes out?
- MP3 (audio/mpeg), usable directly in video editors, web players, and mobile apps without conversion.
- Can GetRun audio be used in monetised video?
- That follows the licence of the provider behind each model. Check the model page for its terms before publishing monetised work.
Other categories
Standards we follow
Full catalog · Price list · Compare models · API documentation · About GetRun