Minimax Speech 02 Turbo

Name: Minimax Speech 02 Turbo
Author: Nodespell Team

Official

Fast MiniMax speech generation with the same main delivery controls as the HD node.

Nodespell AI

AI / Audio / Minimax

Fast MiniMax speech generation with the same main delivery controls as the HD node.

MiniMax Speech 02 Turbo is for quick narration, scratch dialogue, and iteration-heavy voice work. It keeps controls for pitch, speed, volume, emotion, voice ID, sample rate, and language handling.

Use it to test scripts and timing. Move to Speech 02 HD when the delivery direction is approved and quality matters more than speed.

Model Examples (4)

Example Index01 / 04

Example 01

Prestige-series teaser

Trailer-style narration for a dramatic series promo.

Open

Source Inputs01

Text

At first they called it an accident. Then the dailies came back. Every frame showed the same door, open three inches wider than before. This autumn, the footage tells its own story.

Parameters09

Text

At first they called it an accident. Then the dailies came back. Every frame showed the same door, open three inches wider than before. This autumn, the footage tells its own story.

Voice Id

Deep_Voice_Man

Emotion

neutral

Speed

Pitch

Volume

Channel

mono

Sample Rate

Bitrate

ttslow-latency

Response

Inputs (1)

text

String

Text to convert to speech

Multi InputMin: 0Max: 100

Parameters (11)

Text

String

Text to convert to speech. Every character is 1 token. Maximum 5000 characters. Use <#x#> between words to control pause duration (0.01-99.99s).

Default:

Pitch

Number

Speech pitch

Default: 0

Speed

Number

Speech speed

Default: 1

Volume

Number

Speech volume

Default: 1

Bitrate

Number

Bitrate for the generated speech

Default: 128000

Channel

String

Number of audio channels

Default: mono

Emotion

String

Speech emotion

Default: auto

voice_id

String

Desired voice ID. Use an available custom voice ID, or one of the following system voice IDs: Wise_Woman, Friendly_Person, Inspirational_girl, Deep_Voice_Man, Calm_Woman, Casual_Guy, Lively_Girl, Patient_Man, Young_Knight, Determined_Man, Lovely_Girl, Decent_Boy, Imposing_Manner, Elegant_Man, Abbess, Sweet_Girl_2, Exuberant_Girl

Default: Wise_Woman

sample_rate

Number

Sample rate for the generated speech

Default: 32000

language_boost

String

Enhance recognition of specific languages and dialects

Default: None

english_normalization

Boolean

Enable English text normalization for better number reading (slightly increases latency)

Default: false

Outputs (1)

response

Inferred

response

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Keywords

Text To SpeechVoice CloningReal Time

Use in Workflow