Minimax Speech 2.5 Turbo Preview
Playground
Try it on WavespeedAI!MiniMax’s high-definition text-to-speech model, Compared to Speech 02 released in May, Speech 2.5 has three major breakthroughs: stronger multilingual expressiveness, more accurate voice replication, and broader coverage with 40 languages. Your request will cost $0.04 per 1000 characters.
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.
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.
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 ${WAVESPEED_API_KEY}" \
--data-raw '{
"speed": 1,
"volume": 1,
"pitch": 0,
"emotion": "happy",
"english_normalization": false
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${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 | Sample rate of generated sound. |
| bitrate | integer | No | - | 32000, 64000, 128000 | Bitrate of generated sound. |
| channel | string | No | - | 1, 2 | The number of channels of the generated audio. 1: mono, 2: stereo. |
| 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. |
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 Query Parameters
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction, the ID of the prediction to get |
| 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 |