MiniMax Speech 2.8 HD

POST/v1/run

MiniMax Speech 2.8 HD text-to-speech model with high-definition voice synthesis, enhanced expressiveness, 40+ language support, and voice cloning.

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/speech/2.8/hd.

Default: minimax/speech/2.8/hd

stringtextrequired

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

Default: Hello, welcome to Sandbase

stringvoice_idrequired

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

Default: Wise_Woman

Optional<number>speed

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

Range: 0.5 to 2

Default: 1

Optional<number>volume

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

Range: 0.1 to 10

Default: 1

Optional<integer>pitch

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

Range: -12 to 12

Default: 0

Optional<string>emotion

The emotion of the generated speech.

Allowed values: happy, sad, angry, fearful, disgusted, surprised, neutral

Default: happy

Optional<boolean>english_normalization

Improves performance in number-reading scenarios.

Default: false

Optional<integer>sample_rate

Sample rate of generated sound.

Allowed values: 8000, 16000, 22050, 24000, 32000, 44100

Optional<integer>bitrate

Bitrate of generated sound.

Allowed values: 32000, 64000, 128000, 256000

Optional<integer>channel

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

Allowed values: 1, 2

Optional<string>format

Format of generated sound.

Allowed values: mp3, pcm, flac

Optional<string>language_boost

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

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/speech/2.8/hd",
  "text": "Hello, welcome to Sandbase",
  "voice_id": "Wise_Woman"
}'

# 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/speech/2.8/hd",
  "status": "running",
  "outputs": []
}