Audio
Kokoro TTS
Read an English script aloud with Kokoro American English.
- Text to audio
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for Kokoro TTS. Review your own result before publishing.
A starting point.
Use finished narration text rather than a description of a voice. Punctuation helps you plan pauses before generating the recording.
Before you publish.
Listen to names, numbers and abbreviations against the script. Check pacing at the intended playback speed.
Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.
Settings and model questionsCheck the available settings and guidance when preparing your input.
Inputs and settings
Provide nonempty text in prompt and choose a documented American English voice ID through voice, such as af_heart.
Start speed at 1, then adjust only pacing. Raywake accepts 0.1–5; extreme values need listening checks rather than assuming speech stays intelligible.
Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.
Supported inputs
These fields come from the current studio form for kokoro/american-english. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
prompt | Text | Required | Min. characters: 1 |
speed | Number | Optional | ≥ 0.1 · ≤ 5 |
voice | Text | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use Kokoro TTS through the API.
Start with this model ID for the endpoint featured on this page:
kokoro/american-english
Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.
Check the current model schema for supported inputs and options. Other tasks may use different model IDs.
From quote to result.
Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.
Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.