MiniMax Speech 2.8 HD Asynchronous Speech Synthesis
Audio
MiniMax Speech 2.8 HD Asynchronous Speech Synthesis
POST
MiniMax Speech 2.8 HD Asynchronous Speech Synthesis
Use this endpoint to create an asynchronous speech synthesis task. It supports text or file input. Text input is limited to a maximum of 50,000 characters, and file input is limited to a maximum of 100,000 characters.
Request Headers
Enum value:
application/jsonBearer authentication format: Bearer {{API Key}}.
Request Body
The text to synthesize into audio, limited to a maximum of 50,000 characters. Either
• Vocalization tags: Only when the model is
text or text_file_id is required• Vocalization tags: Only when the model is
speech-2.8-hd or speech-2.8-turbo, vocalization tags can be inserted into the text. Supported vocalizations: (laughs) (laughter), (chuckle) (chuckle), (coughs) (cough), (clear-throat) (clear throat), (groans) (groan), (breath) (normal breathing), (pant) (panting), (inhale) (inhale), (exhale) (exhale), (gasps) (gasp), (sniffs) (sniff), (sighs) (sigh), (snorts) (snort), (burps) (burp), (lip-smacking) (lip smacking), (humming) (humming), (hissing) (hissing), (emm) (um), (whistles) (whistle), (sneezes) (sneeze), (crying) (sobbing), (applause) (applause)The text file id to synthesize into audio. A single file must be less than 100,000 characters. Supported file formats: txt, zip. Either
• txt file: length limit <100000 characters. Supports using
• zip file:
• The compressed package must contain txt or json files in the same format.
• json file format: supports three fields: [
text_file_id or text is required. The format is automatically validated after being passed in.• txt file: length limit <100000 characters. Supports using
<#x#> to mark custom pauses. x is the pause duration (unit: seconds), with a range of [0.01, 99.99], and up to two decimal places. Note that pauses must be set between two pieces of text that can be pronounced, and multiple pause markers cannot be used consecutively• zip file:
• The compressed package must contain txt or json files in the same format.
• json file format: supports three fields: [
title, content, extra], representing the title, body, and additional information respectively. If all three fields exist, 3 groups of results are produced, for a total of 9 files, all stored in one folder. If a field does not exist or its content is empty, no corresponding result will be generated for that fieldControls whether to add an audio rhythm identifier at the end of the synthesized audio. The default value is False. This parameter only takes effect for non-streaming synthesis
Whether to enhance recognition capability for specified low-resource languages and dialects. The default value is
null. It can be set to auto to let the model determine automatically.Available 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, Persian, Slovak, Swedish, Croatian, Filipino, Hungarian, Norwegian, Slovenian, Catalan, Nynorsk, Tamil, Afrikaans, autoEnable this parameter to make clause transitions more natural. Only the
speech-2.8-hd and speech-2.8-turbo models are supportedResponse Information
The ID of the corresponding audio file returned after the task is created successfully.
• After the task is completed, you can query using file_id. This field is not returned when the request errorsNote: The returned download URL is valid for 9 hours (32400 seconds) from the time it is generated. After expiration, the file will become invalid and the generated information will be lost. Please pay attention to the time limit for downloading the information
• After the task is completed, you can query using file_id. This field is not returned when the request errorsNote: The returned download URL is valid for 9 hours (32400 seconds) from the time it is generated. After expiration, the file will become invalid and the generated information will be lost. Please pay attention to the time limit for downloading the information
Use task_id to request the Get Task Result API to retrieve the generated output.
Key information used to complete the current task
Number of billable characters