Minimax Speech 2.5 Turbo Preview

Playground

Minimax Speech 2.5 Turbo Preview: HD TTS with multilingual support, accurate voice replication across 40 languages. $0.04/1000 chars. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

MiniMax Speech 2.5 Turbo Preview

MiniMax’s high-definition text-to-speech model with natural pronunciation and clear articulation. Features multiple voice options, adjustable speed, volume, and pitch controls for professional-grade audio generation.

Features

Three major breakthroughs: stronger multilingual performance, more lifelike tone, and 40 languages covered — now with real-time streaming capabilities for low-latency audio generation.

Leapfrogging multilingual performance

Chinese is the world’s strongest, English and other languages have been comprehensively improved in terms of accuracy, similarity, and natural rhythm, surpassing the previous generation Speech 02.
English similarity has been significantly improved, and 40 languages can be switched at will, making it no longer “mechanical” in commercial meetings, daily conversations, and English podcasts.

Lifelike tone replication

Across languages, accents, styles, and emotions, with industry-leading precision in detail.
The model can still achieve “voice”-like realism in extreme scenarios, such as cross-language accent preservation, regional accent preservation, and special age voice replication.

40 languages are now supported

Diversified high-quality audio library, globalized and unobstructed.
New additions include Bulgarian, Danish, Hebrew, Malay, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans… …
Cross-border e-commerce, overseas customer service, and localized marketing are now easier than ever with globalized content creation at your fingertips.
Streaming mode: generate and play audio as it’s being synthesized for real-time applications.

Voice ID List

We offer a rich, built-in library of multi-lingual voices. For a detailed list, please refer to this document.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/minimax/speech-2.5-turbo-preview" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "speed": 1,
    "volume": 1,
    "pitch": 0,
    "emotion": "happy",
    "english_normalization": false,
    "enable_sync_mode": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

Parameter	Type	Required	Default	Range	Description
text	string	Yes	-	-	Text to convert to speech. Every character is 1 token. Maximum 10000 characters. Use <#x#> between words to control pause duration (0.01-99.99s).
voice_id	string	Yes	-	-	Desired voice ID. Use a voice ID you have trained (https://wavespeed.ai/models/minimax/voice-clone), 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.
speed	number	No	1	0.50 ~ 2.00	Speech speed. Range: 0.5-2.0, where 1.0 is normal speed.
volume	number	No	1	0.10 ~ 10.00	Speech volume. Range: 0.1-10.0, where 1.0 is normal volume.
pitch	number	No	-	-12 ~ 12	Speech pitch. Range: -12 to 12, where 0 is normal pitch.
emotion	string	No	happy	happy, sad, angry, fearful, disgusted, surprised, neutral	The emotion of the generated speech.
english_normalization	boolean	No	false	-	This parameter supports English text normalization, which improves performance in number-reading scenarios.
sample_rate	integer	No	-	8000, 16000, 22050, 24000, 32000, 44100	Sample rate of generated sound.
bitrate	integer	No	-	32000, 64000, 128000, 256000	Bitrate of generated sound.
channel	string	No	-	1, 2	The number of channels of the generated audio. 1: mono, 2: stereo.
format	string	No	-	mp3, wav, pcm, flac	Format of generated sound.
language_boost	string	No	-	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, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans, auto	Enhance the ability to recognize specified languages and dialects.
enable_sync_mode	boolean	No	false	-	If set to true, the function will wait for the result to be generated and uploaded before returning the response. It allows you to get the result directly in the response. This property is only available through the API.

Response Parameters

Parameter	Type	Description
code	integer	HTTP status code (e.g., 200 for success)
message	string	Status message (e.g., “success”)
data.id	string	Unique identifier for the prediction, Task Id
data.model	string	Model ID used for the prediction
data.outputs	array	Array of URLs to the generated content (empty when status is not `completed`)
data.urls	object	Object containing related API endpoints
data.urls.get	string	URL to retrieve the prediction result
data.has_nsfw_contents	array	Array of boolean values indicating NSFW detection for each output
data.status	string	Status of the task: `created`, `processing`, `completed`, or `failed`
data.created_at	string	ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.error	string	Error message (empty if no error occurred)
data.timings	object	Object containing timing details
data.timings.inference	integer	Inference time in milliseconds

Result Request Parameters

Minimax Speech 2.5 Hd Preview Minimax Speech 2.6 Hd