curl --request POST \
  --url https://api.modellix.ai/api/v1/minimax/minimax-voice-clone \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "speech-2.8-turbo",
  "audio_url": "https://example.com/reference.wav",
  "text": "Welcome to Modellix speech synthesis."
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-minimax-voice-clone-001",
    "model_id": "minimax/minimax-voice-clone",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-minimax-voice-clone-001"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

MiniMax One-shot Voice Clone + TTS

[Core Function] MiniMax Voice Clone clones a speaker from a public reference audio URL and synthesizes new speech in one async request; only the final audio is returned. [Strengths] No voice enrollment management; optional language_boost for clone and synthesis; prosody controls (speed, volume, pitch, emotion); pronunciation overrides; voice effects; flexible audio formats. [Best For] One-off cloned narration, personalized prompts, and demos where a lasting voice library is not needed. [Limitations] Do NOT use this to obtain a reusable voice library entry; the cloned voice is temporary and is not returned. audio_url must be publicly reachable (mp3/m4a/wav, 10s–5min, ≤20 MB). [Routing] Choose speech-2.8-hd for higher quality; speech-2.8-turbo for lower latency or cost. Paralinguistic tags such as (laughs) in text are supported on both speech-2.8-hd and speech-2.8-turbo.

POST

minimax

minimax-voice-clone

curl --request POST \
  --url https://api.modellix.ai/api/v1/minimax/minimax-voice-clone \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "speech-2.8-turbo",
  "audio_url": "https://example.com/reference.wav",
  "text": "Welcome to Modellix speech synthesis."
}
'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-minimax-voice-clone-001",
    "model_id": "minimax/minimax-voice-clone",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-minimax-voice-clone-001"
    }
  }
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

{
  "code": 400,
  "message": "Invalid parameters: model is required"
}

Authorizations

Authorization

string

header

required

Modellix API Key. Format: Bearer <your_api_key>

Body

application/json

One-shot voice clone + TTS request. Required: model, audio_url, text. Optional: prompt_audio/prompt_text, clone processing, language_boost, AIGC watermark, TTS prosody/audio/pronunciation/voice effects, and subtitles. The cloned voice is temporary and is not returned.

model

enum<string>

required

Supported MiniMax speech model for both voice clone and TTS in this request.

Available options:

speech-2.8-hd,

speech-2.8-turbo

Example:

"speech-2.8-turbo"

audio_url

string

required

Primary reference audio URL for cloning. Must be publicly accessible without auth. Formats: mp3, m4a, wav. Duration 10 seconds–5 minutes. File size ≤20 MB. Distinct from prompt_audio.

Required string length: 1 - 2048

Example:

"https://example.com/reference.wav"

text

string

required

Text to synthesize with the temporarily cloned voice. Required. Fewer than 10,000 Unicode characters. On speech-2.8-hd / speech-2.8-turbo, may include paralinguistic tags such as (laughs), (breath), or (sighs).

Required string length: 1 - 9999

Example:

"Welcome to Modellix speech synthesis."

prompt_audio

string

Optional short example audio URL to improve clone similarity and stability. Not a substitute for audio_url. Formats: mp3, m4a, wav. Duration must be under 8 seconds. File size ≤20 MB.

Required string length: 1 - 2048

Example:

"https://example.com/short-sample.wav"

prompt_text

string

Optional transcript matching prompt_audio. Must align with the example audio content; end with punctuation. Not a substitute for text.

Required string length: 1 - 1000

Example:

"Short sample content."

need_noise_reduction

boolean

default:false

Whether to enable noise reduction on the clone reference audio. Default false.

Example:

false

need_volume_normalization

boolean

default:false

Whether to enable volume normalization for cloning. Default false.

Example:

false

language_boost

enum<string>

Optional language or dialect boost for both cloning and synthesis. Omit for default behavior. Use auto to let the model decide.

Available options:

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

Example:

"Chinese"

aigc_watermark

boolean

default:false

Whether to append an AIGC watermark to the returned audio. Default false.

Example:

false

speed

number

default:1

Speech rate multiplier for synthesis. Default 1.0. Range [0.5, 2.0].

Required range: 0.5 <= x <= 2

Example:

1

vol

number

default:1

Speech volume for synthesis. Default 1.0. Range (0.0, 10.0].

Required range: x <= 10

Example:

1

pitch

integer

default:0

Pitch adjustment in semitones. Default 0. Range [-12, 12]. Distinct from modify_pitch (voice effect).

Required range: -12 <= x <= 12

Example:

0

emotion

enum<string>

Optional emotion control. Leave unset to let the model infer from text.

Available options:

happy,

sad,

angry,

fearful,

disgusted,

surprised,

calm

Example:

"happy"

text_normalization

boolean

default:false

Enable Chinese/English text normalization for better number reading; may add slight latency. Default false.

Example:

false

latex_read

boolean

default:false

Enable reading LaTeX formulas aloud (Chinese only). When true, language_boost may be forced to Chinese. Wrap formulas with $$ and escape backslashes. Default false.

Example:

false

sample_rate

enum<integer>

default:32000

Output sample rate in Hz. Default 32000.

Available options:

8000,

16000,

22050,

24000,

32000,

44100

Example:

32000

bitrate

enum<integer>

default:128000

Audio bitrate. Default 128000. Only effective when format is mp3; ignored for other formats.

Available options:

32000,

64000,

128000,

256000

Example:

128000

format

enum<string>

default:mp3

Output audio encoding format. Default mp3. Result audio is returned as a URL on the completed task.

Available options:

mp3,

pcm,

flac,

wav

Example:

"mp3"

channel

enum<integer>

default:1

Output channel count. 1 is mono, 2 is stereo. Default 1.

Available options:

1,

2

Example:

1

force_cbr

boolean

default:false

Force constant bitrate encoding. Optional; typically unused for standard async synthesis. Default false.

Example:

false

pronunciation_tone

string[]

Custom pronunciation rules. Use / as separator. For Mandarin entries, tones are digits 1-5 (5=neutral), e.g. name/(yan4)(shao3)(fei1). Example: ["omg/oh my god"].

Example:

["omg/oh my god"]

modify_pitch

integer

Voice effect pitch: lower is deeper, higher is brighter. Range [-100, 100]. Distinct from pitch (semitone).

Required range: -100 <= x <= 100

Example:

0

modify_intensity

integer

Voice effect intensity: lower is stronger, higher is softer. Range [-100, 100].

Required range: -100 <= x <= 100

Example:

0

modify_timbre

integer

Voice effect timbre: lower is thicker, higher is brighter or crisper. Range [-100, 100].

Required range: -100 <= x <= 100

Example:

0

sound_effects

enum<string>

Optional sound effect applied to the output. Supported for mp3, wav, and flac.

Available options:

spacious_echo,

auditorium_echo,

lofi_telephone,

robotic

Example:

"spacious_echo"

subtitle_enable

boolean

default:false

Whether to generate a subtitle download link. Default false.

Example:

false

Response

Task submitted successfully. Poll GET /api/v1/tasks/{task_id} until the task completes; synthesized audio is returned on the task result.

Response object for asynchronous task submission.

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Task submission details. Poll GET /api/v1/tasks/{task_id} until status is success; audio appears in result.resources.

Show child attributes

Minimax t2v 01 director Speech 2 8 hd

Model API

Common API

File API

MiniMax One-shot Voice Clone + TTS

Authorizations

Body

Response