TRStart creating
Menu

MiniMax Speech 2.8 [HD]

Generate speech from text prompts and different voices using the MiniMax Speech-2.8 HD model, which leverages advanced AI techniques to create high-quality text-to-speech.

Input

Fields marked * are required. Review the price before generating.

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).

Additional settings

Voice configuration settings

Predefined voice ID to use for synthesis

Speech speed (0.5-2.0)

Volume (0-10)

Voice pitch (-12 to 12)

Emotion of the generated speech

Enables English text normalization to improve number reading performance, with a slight increase in latency

Audio configuration settings

Sample rate of generated audio

Bitrate of generated audio

Audio format

Number of audio channels (1=mono, 2=stereo)

Enhance recognition of specified languages and dialects

Custom pronunciation dictionary for text replacement

List of pronunciation replacements in format ['text/(pronunciation)', ...]. For Chinese, tones are 1-5. Example: ['燕少飞/(yan4)(shao3)(fei1)']

Loudness normalization settings for the audio

Enable loudness normalization for the audio

Target loudness in LUFS (default -18.0)

Target loudness range in LU (default 8.0)

Target peak level in dBTP (default -0.5).

Voice modification settings for Speech 2.8 models.

Pitch adjustment in semitones. Range: -100 to 100. Positive values raise pitch, negative values lower it.

Intensity/energy of the voice. Range: -100 to 100. Higher values create more energetic speech.

Timbre adjustment. Range: -100 to 100. Affects the tonal quality of the voice.

Price$0.17 / run

You sign up first. Your settings are kept.

API code for this input

Complete the required fields and fix input errors to see API code.

How to use MiniMax Speech 2.8 [HD]

Getting started

Write the actual script and use pauses deliberately.

Review your result

Listen for pronunciation, pacing and whether expressive sounds fit the passage.

Inputs and settings

This version takes prompt, with a 10000-character Raywake limit. voice_setting selects voice configuration; pronunciation_dict supports pronunciation adjustments.

audio_setting, normalization_setting and voice_modify configure audio and voice treatment. The documented <#x#> pause notation belongs inside the spoken script.

We use analytics cookies. Privacy policy