MiniMax Speech-02-turbo Synchronous Speech Synthesis
Audio
MiniMax Speech-02-turbo Synchronous Speech Synthesis
POST
MiniMax Speech-02-turbo Synchronous Speech Synthesis
This API supports synchronous text-to-speech generation, with a maximum of 10,000 characters per text submission. It supports 100+ system voices and selectable cloned voices; adjustment of volume, pitch, speed, and output format; proportional voice mixing and fixed interval control; multiple audio specifications and formats, including mp3, pcm, flac, and wav; and streaming output.
After submitting a long-text speech synthesis request, note that the returned url is valid for 24 hours from the time the url is returned. Please download the information in time.
Request Headers
Enum value:
application/jsonBearer authentication format: Bearer {{API Key}}.
Request Body
The text to synthesize. The length limit is less than 10,000 characters. Use line breaks to separate paragraphs. (If you need to control the interval time within the speech, add <#x#> between characters, where x is in seconds. Supported range: 0.01–99.99, with up to two decimal places.) Custom speech time intervals between text segments are supported to achieve custom pause durations in synthesized speech. Note that the text interval must be set between two pieces of pronounceable text, and multiple consecutive time intervals cannot be set.
Required as an alternative to voice_id
Whether to stream. Default is false, meaning streaming is not enabled.
Enhances recognition capability for the specified low-resource language or dialect. After setting it, speech performance can be improved in the specified low-resource language/dialect scenario. If the language type is not clear, you can select “auto”, and the model will determine the language type automatically. Supported 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', 'auto'Parameter that controls the output result format. Optional values are
url and hex. Default value is hex. This parameter only takes effect in non-streaming scenarios. Streaming scenarios only support returning results in hex format. The returned url is valid for 24 hours.Voice effects settings. This parameter supports the following audio formats:
- Non-streaming: mp3, wav, flac
- Streaming: mp3
Response Information
The synthesized audio segment, encoded in hex and generated according to the input-defined format (
audio_setting.format) (mp3/pcm/flac). The return format depends on the definition of output_format. When stream is true, only hex return format is supported.The current audio stream status, returned only when
stream is true. 1 indicates synthesis in progress, and 2 indicates synthesis has ended.