minimax/speech/2.6/turbo

Name: MiniMax Speech 2.6 Turbo
Author: MiniMax

MiniMax Speech 2.6 Turbo text-to-speech model with fast voice synthesis, 40+ language support, voice cloning, and expressive emotion control.

Input

Text(string)

Text to convert to speech. Use <#x#> between words to control pause duration (0.01-99.99s).

Voice(string)

Voice ID for speech synthesis. Use a predefined system voice or a custom cloned voice ID.

Speed(number)

0.52

Speech speed. Range: 0.5-2.0, where 1.0 is normal speed. Range: 0.5 to 2.

Volume(number)

0.110

Speech volume. Range: 0.1-10.0, where 1.0 is normal volume. Range: 0.1 to 10.

Pitch(integer)

-1212

Speech pitch. Range: -12 to 12, where 0 is normal pitch. Range: -12 to 12.

Emotion(string)

The emotion of the generated speech. Allowed values: happy, sad, angry, fearful, disgusted, surprised, neutral.

English Normalization(boolean)

Improves performance in number-reading scenarios.

Sample Rate(integer)

Sample rate of generated sound. Allowed values: 8000, 16000, 22050, 24000, 32000, 44100.

Bitrate(integer)

Bitrate of generated sound. Allowed values: 32000, 64000, 128000, 256000.

Channel(integer)

The number of channels. 1: mono, 2: stereo. Allowed values: 1, 2.

Format(string)

Format of generated sound. Allowed values: mp3, pcm, flac.

Language Boost(string)

Enhance the ability to recognize specified languages and dialects. Allowed values: Chinese, Chinese,Yue, English, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Slovak, Swedish, Croatian, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Afrikaans, auto.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDminimax/speech/2.6/turbo

Input Schema

12 parameters · 2 required · 10 optional

Parameter	Type	Required	Description
`text`	string	Required	Text to convert to speech. Use <#x#> between words to control pause duration (0.01-99.99s). · Min length: 1 · Max length: 5000 · Default: "Hello, welcome to Sandbase"
`voice_id`	string	Required	Voice ID for speech synthesis. Use a predefined system voice or a custom cloned voice ID. · Default: "Wise_Woman"
`pitch`	integer	Optional	Speech pitch. Range: -12 to 12, where 0 is normal pitch. · Min: -12 · Max: 12 · Default: 0
`speed`	number	Optional	Speech speed. Range: 0.5-2.0, where 1.0 is normal speed. · Min: 0.5 · Max: 2 · Default: 1
`format`	string	Optional	Format of generated sound. · Options: mp3, pcm, flac mp3pcmflac
`volume`	number	Optional	Speech volume. Range: 0.1-10.0, where 1.0 is normal volume. · Min: 0.1 · Max: 10 · Default: 1
`bitrate`	integer	Optional	Bitrate of generated sound. · Options: 32000, 64000, 128000, 256000 3200064000128000256000
`channel`	integer	Optional	The number of channels. 1: mono, 2: stereo. · Options: 1, 2 12
`emotion`	string	Optional	The emotion of the generated speech. · Options: happy, sad, angry, fearful, disgusted, surprised, neutral · Default: "happy" happysadangryfearfuldisgustedsurprisedneutral
`sample_rate`	integer	Optional	Sample rate of generated sound. · Options: 8000, 16000, 22050, 24000, 32000, 44100 80001600022050240003200044100
`language_boost`	string	Optional	Enhance the ability to recognize specified languages and dialects. · Options: Chinese, Chinese,Yue, English, Arabic, Russian, Spanish, French, Portuguese, German, Turkish, Dutch, Ukrainian, Vietnamese, Indonesian, Japanese, Italian, Korean, Thai, Polish, Romanian, Greek, Czech, Finnish, Hindi, Bulgarian, Danish, Hebrew, Malay, Slovak, Swedish, Croatian, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Afrikaans, auto ChineseChinese,YueEnglishArabicRussianSpanishFrenchPortugueseGermanTurkishDutchUkrainianVietnameseIndonesianJapaneseItalianKoreanThaiPolishRomanianGreekCzechFinnishHindiBulgarianDanishHebrewMalaySlovakSwedishCroatianHungarianNorwegianSlovenianCatalanNynorskAfrikaansauto
`english_normalization`	boolean	Optional	Improves performance in number-reading scenarios. · Default: false

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "minimax/speech/2.6/turbo",
  "text": "Hello, welcome to Sandbase",
  "pitch": 0,
  "speed": 1,
  "volume": 1,
  "emotion": "happy",
  "voice_id": "Wise_Woman",
  "english_normalization": false,
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to MiniMax Speech 2.6 Turbo

API README

Speech 2.6 Turbo

Speech 2.6 Turbo is built for expressive speech synthesis, with this exact route focused on voice and delivery control. MiniMax Speech 2.6 Turbo text-to-speech model with fast voice synthesis, 40+ language support, voice cloning, and expressive emotion control. It is designed for production workflows that need a clearly scoped media operation instead of a generic assistant response, preserving the supplied direction while returning an artifact ready for review, iteration, or downstream assembly.

The request surface keeps creative direction and delivery choices explicit through text, pitch, speed, format, volume, bitrate. Teams can lock source material, describe the intended result, choose supported output controls, and rerun the same request structure across variations. This makes experiments easier to compare and larger pipelines easier to operate without hiding important decisions inside an opaque preset.

Highlights

Voice And Delivery Control. The minimax/speech/2.6/turbo route is dedicated to voice and delivery control, keeping inputs and outputs matched to this operation.
Multilingual Spoken Content. Within minimax/speech/2.6/turbo, documented prompt and media controls direct multilingual spoken content while keeping the brief close to the result.
Natural Long-Form Narration. The minimax/speech/2.6/turbo result provides natural long-form narration in a machine-consumable form for review and downstream production.
Route-specific control. For minimax/speech/2.6/turbo, documented controls include text, pitch, speed, format, volume, bitrate, defining the supported variation space for this exact route.

Pricing

Configuration	Price
1,000 characters	`$0.060`
Per character	`$0.0000600`

When to Use

Scenario	Why it fits
Choose this route	When the deliverable is specifically voice and delivery control, not a neighboring generation or editing task.
Production iteration	When creative teams need repeatable multilingual spoken content with an explicit request payload.
Automated pipelines	When natural long-form narration must flow into review, storage, compositing, or publishing.
Controlled variations	When a stable brief should be rerun while changing only documented inputs.
Prototype to scale	When the same `minimax/speech/2.6/turbo` contract should serve a single experiment and a larger batch later.

Prompt Guide

Lead with the subject or source, then state the transformation, important spatial or temporal details, style, and finish. Supply only documented fields, keep media URLs reachable, and vary one control at a time when comparing outputs.

{
  "text": "A directed creative request with subject, setting, style, motion, and finish.",
  "voice_id": "value"
}

Technical Specs

Property	Value
Model ID	`minimax/speech/2.6/turbo`
Required inputs	`text`, `voice_id`
`text`	string
`pitch`	integer
`speed`	number
`format`	string
`volume`	number
`bitrate`	integer
`channel`	integer
`emotion`	string
`voice_id`	string
`sample_rate`	integer
`audio_setting`	object
`output_format`	string; options: url, hex; default: hex
`voice_setting`	object
`language_boost`	string
`english_normalization`	boolean
`sync_mode`	boolean; default: false
`safety_tolerance`	string; default: 6
`pronunciation_dict`	string

Related Models

minimax/speech/02-hd
minimax/speech/02-turbo
minimax/speech/2.6/hd