MiniMax Speech (T2A)
Synthesizes audio from the input text and returns the audio bytes directly. Billing is per input character.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
The speech model to use. hd variants prioritize fidelity, turbo variants prioritize latency.
speech-2.8-hd, speech-2.8-turbo, speech-2.6-hd, speech-2.6-turbo, speech-02-hd, speech-02-turbo, speech-01-hd, speech-01-turbo "speech-2.8-hd"
The text to synthesize. Billed per character.
"你好,欢迎使用语音合成服务。"
MiniMax voice ID, e.g. male-qn-qingse, female-shaonv. Passed through to the provider as voice_id.
"male-qn-qingse"
Audio container format of the response.
mp3, wav, flac, aac, pcm Playback speed multiplier.
0.5 <= x <= 2Provider-specific fields merged into the upstream MiniMax request, e.g. {"voice_setting": {"emotion": "happy"}, "audio_setting": {"sample_rate": 32000}, "language_boost": "Chinese"}. Set {"output_format": "url"} to receive a 302 redirect to the audio URL instead of raw bytes.
Response
Audio synthesized successfully; the response body is the audio file.
The response is of type file.