Audio
MiniMax Speech-02 HD
Convert written text to speech with MiniMax Speech-02 HD.
- Text to speech
Sign in to create. Review the credit cost in the studio before running.
Catalog preview for MiniMax Speech-02 HD. Review your own result before publishing.
A starting point.
Prepare narration with readable punctuation and clearly written names.
Before you publish.
Listen for mispronounced names, rushed pauses and unexpected number readings.
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
Put the spoken script in text, not prompt. Raywake accepts up to 5000 characters; voice_setting and audio_setting hold voice and audio configuration.
language_boost and pronunciation_dict can guide language handling and pronunciation. Review a short passage containing your difficult words before preparing the full narration.
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 minimax/speech-02-hd. Other modes may require different inputs.
| Input | Type | Requirement | Options and limits |
|---|---|---|---|
text | Text | Required | Min. characters: 1 · Max. characters: 5000 |
audio_setting | Object | Optional | — |
language_boost | Text | Optional | — |
pronunciation_dict | Object | Optional | — |
voice_setting | Object | Optional | — |
Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.
Use MiniMax Speech-02 HD through the API.
Start with this model ID for the endpoint featured on this page:
minimax/speech-02-hd
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.