← All models
Generate speech from text prompts and different voices using the MiniMax Speech-2.8 Turbo model, which leverages advanced AI techniques to create high-quality text-to-speech.
Details
- Accepts
- text
Pricing
- Price
- 0.00750 cr / character
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| promptrequired | string | Text to convert to speech. Use `<#x#>` for pauses (x = 0.01-99.99 seconds). Supports interjection tags: `(laughs)`, `(sighs)`, `(coughs)`, `(clears throat)`, `(gasps)`, `(sniffs)`, `(groans)`, `(yawns)`. |
| voice_modify | — | Voice modification settings to adjust pitch, intensity, and timbre. |
| audio_setting | — | Audio configuration settings |
| output_format | stringenum: url, hex | Format of the output content (non-streaming only) |
| voice_setting | — | Voice configuration settings |
| language_boost | — | Enhance recognition of specified languages and dialects |
| pronunciation_dict | — | Custom pronunciation dictionary for text replacement |
| enable_safety_checker | boolean | Authorized callers may set false to request relaxed screening. |
| normalization_setting | — | Loudness normalization settings for the audio |
Output
| Field | Type | Description |
|---|---|---|
| audio | — | The generated audio file |
| duration_ms | integer | Duration of the audio in milliseconds |