{"input_schema":{"type":"object","properties":{"text":{"type":"string","description":"What to say.","examples":["Hello, and welcome back to the show."],"maxLength":10000},"voice_setting":{"type":"object","description":"Which voice to use and how it delivers: `voice_id`, `speed`, `vol`, `pitch`, and an emotional register.","examples":[{"voice_id":"female-shaonv","speed":1,"vol":1,"pitch":0}]},"audio_setting":{"type":"object","description":"How to encode the audio: `format`, `sample_rate`, `bitrate`, and `channel`.","examples":[{"format":"mp3","sample_rate":32000,"bitrate":128000,"channel":1}]},"language_boost":{"type":"string","description":"A language hint that improves pronunciation.","examples":["English"]}},"required":["text"],"additionalProperties":true,"examples":[{"text":"Hello, and welcome back to the show.","voice_setting":{"voice_id":"female-shaonv","speed":1},"audio_setting":{"format":"mp3","sample_rate":32000}}]},"output_schema":{"type":"object","description":"The audio, returned inline, with its length, sample rate, size, and the character count that was billed.","additionalProperties":true},"addons_schema":{"type":"object","additionalProperties":false},"capability_id":"minimax.tts","session_compatible":true,"pricing_available":true,"id":"minimax/speech-02-hd","object":"endpoint","provider":"minimax","endpoint":"speech-02-hd","model_category":"audio","name":"Speech 02 HD","summary":"Turn text into spoken audio in a chosen voice.","description":"Converts a block of text into speech using a stock or previously cloned voice. This is the legacy high-definition tier, which favours fidelity over speed. Voice settings control delivery — speaking rate, volume, pitch, and an emotional register such as calm — while audio settings control the encoding: container format, sample rate, bitrate, and mono or stereo. A language hint improves pronunciation for a particular language or dialect. Billing counts the characters submitted, so the price of a call is known before it is made.","unit":"character","price_per_unit":"0.00007","list_price_per_unit":"0.0001","reports_cost":false,"input_fields":[{"name":"text","type":"string","required":true,"description":"What to say.","example":"Hello, and welcome back to the show.","max":10000},{"name":"voice_setting","type":"object","required":false,"description":"Which voice to use and how it delivers: `voice_id`, `speed`, `vol`, `pitch`, and an emotional register.","example":{"voice_id":"female-shaonv","speed":1,"vol":1,"pitch":0}},{"name":"audio_setting","type":"object","required":false,"description":"How to encode the audio: `format`, `sample_rate`, `bitrate`, and `channel`.","example":{"format":"mp3","sample_rate":32000,"bitrate":128000,"channel":1}},{"name":"language_boost","type":"string","required":false,"description":"A language hint that improves pronunciation.","example":"English"}],"example_request":{"provider":"minimax","endpoint":"speech-02-hd","input":{"text":"Hello, and welcome back to the show.","voice_setting":{"voice_id":"female-shaonv","speed":1},"audio_setting":{"format":"mp3","sample_rate":32000}}},"output":"The audio, returned inline, with its length, sample rate, size, and the character count that was billed.","limits":{"request_bytes":1000000,"timeout_ms":300000,"input_characters":{"field":"text","max":10000},"audio_bytes":null}}