Minimax

POST/v1/run

Preview Speech 2.5 Hd is MiniMax's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to minimax/preview/speech-2.5-hd.

Default: minimax/preview/speech-2.5-hd

Optional<string>text

Text to convert to speech (max 5000 characters, minimum 1 non-whitespace character)

Default: Hello, welcome to Sandbase

Optional<string>output_format

Format of the output content (non-streaming only)

Allowed values: url, hex

Default: hex

Optional<string>pronunciation_dict

Custom pronunciation dictionary for text replacement

Optional<string>audio_setting

Audio configuration settings

Optional<string>language_boost

Enhance recognition of specified languages and dialects

Allowed values: Persian, Filipino, Tamil, 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

Optional<string>voice_setting

Voice configuration settings

Default: [object Object]

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-speech

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/preview/speech-2.5-hd",
  "text": "Hello, welcome to Sandbase",
  "output_format": "hex"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "minimax/preview/speech-2.5-hd",
  "status": "running",
  "outputs": []
}