Create speech
minimax_create_speechConvert text to speech with a MiniMax voice (speech-2.8-hd, speech-2.8-turbo, speech-2.6-hd, speech-2.6-turbo, speech-2.5-hd-preview, speech-2.5-turbo-preview, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo; default speech-2.8-hd), up to 5000 characters on -hd models and 10000 on -turbo. voice_id comes from minimax_list_voices (built-in or cloned with minimax_clone_voice); emotion and language_boost values from minimax_get_speech_config. Billed per character in the account's MiniMax Audio credits (the subscription music uses, not Hailuo video credits; 412 without them); too many at once on an account answers 429. Waits up to ~50 s and returns the audioId and, once done, audio_url; else call minimax_get_speech. POST /speech/create.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"text": "<text>",
"voice_id": "<voice_id>"
},
"name": "minimax_create_speech"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| vol | No | Volume, 1 or more (default 1). | |
| text | Yes | The words to speak, 1-5000 characters on -hd models, up to 10000 on -turbo. Supports MiniMax's inline markup for emotion, sounds and pauses (see the POST speech/create docs page). | |
| wait | No | Wait up to ~50 s for the job to finish (default true); false returns the id at once. | |
| model | No | Default speech-2.8-hd. -turbo models take longer text and use fewer credits per character. | |
| pitch | No | Pitch, -12 to 12 (default 0). | |
| speed | No | Playback rate, 0.5-2 (default 1). | |
| account | No | The MiniMax account id (minimax_list_accounts) to generate on (a cloned voice_id picks its own account). Required when you have several MiniMax accounts; with one it may be left out. | |
| emotion | No | Default Auto. A value from t2a_emotion of minimax_get_speech_config; or leave it out and mark up the text. | |
| robotic | No | Effect switch (default false). | |
| replyRef | No | Optional reference of yours, stored and returned with the result and webhook. Up to 1,024 characters. | |
| replyUrl | No | Optional webhook: the API POSTs the finished result (same shape as the get tool's record) to this URL. Up to 1,024 characters. | |
| voice_id | Yes | A voice_id from minimax_list_voices: a MiniMax voice id, or the voice_id of a cloned voice (that voice's account is used). | |
| nasal_crisp | No | Voice effect, -100 to 100 (default 0). | |
| spacious_echo | No | Effect switch (default false). | |
| deepen_lighten | No | Voice effect, -100 to 100 (default 0). | |
| language_boost | No | Bias pronunciation toward one language (default Auto): a language name from minimax_get_speech_config (voice_tag_language). | |
| lofi_telephone | No | Effect switch (default false). | |
| auditorium_echo | No | Effect switch (default false). | |
| stronger_softer | No | Voice effect, -100 to 100 (default 0). |