---
canonical_url: "https://docs.composio.dev/toolkits/minimax"
markdown_url: "https://docs.composio.dev/toolkits/minimax.md"
product: "platform"
version: null
last_updated: null
---

# MiniMax

MiniMax provides multimodal AI APIs for text, video, speech, image, music, and file workflows.

- **Category:** artificial intelligence
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 34
- **Triggers:** 0
- **Slug:** `MINIMAX`
- **Version:** 20261015_00
- **Instant:** Supported on the latest version. Support varies by tool.

## Tools

### Clone Voice

**Slug:** `MINIMAX_CLONE_VOICE`

Create a reusable MiniMax cloned voice from an uploaded voice sample, optionally generating paid preview audio.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | string | No | Optional paid preview text. When supplied, model is also required. |
| `model` | string ("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") | No | Speech model for preview audio. Required with text. |
| `file_id` | string | Yes | Uploaded voice_clone audio file ID. Audio must be MP3, M4A, or WAV, 10 seconds to 5 minutes, and no larger than 20 MB. |
| `accuracy` | number | No | ASR similarity threshold from 0 to 1; zero or omission uses provider default 0.7. |
| `voice_id` | string | Yes | Unique custom voice ID, 8-256 characters, starting with a letter and not ending with '-' or '_'. |
| `clone_prompt` | object | No | Optional short prompt sample and exact transcript to improve clone similarity. |
| `aigc_watermark` | boolean | No | Whether to append an AIGC watermark tone to preview audio. |
| `language_boost` | string ("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") | No | Documented language or dialect boost, or auto. |
| `text_validation` | string | No | Expected transcript used for optional ASR similarity validation. |
| `need_noise_reduction` | boolean | No | Whether to apply noise reduction to the cloning sample. |
| `need_volume_normalization` | boolean | No | Whether to normalize cloning-sample volume. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Count Message Tokens

**Slug:** `MINIMAX_COUNT_MESSAGE_TOKENS`

Count input tokens for an Anthropic-compatible message payload without generating content.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | Yes | Text model ID whose tokenizer and request overhead to use. Call MINIMAX_LIST_TEXT_MODELS to discover currently available IDs. |
| `tools` | array | No | Anthropic-compatible tool definitions whose prompt overhead is counted. |
| `system` | string | No | System prompt text or system content blocks included in the count. |
| `messages` | array | Yes | Messages in Anthropic format, including text or content blocks to count. |
| `thinking` | object | No | Thinking configuration included in the token estimate. |
| `tool_choice` | object | No | Tool-selection configuration included in the token estimate. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Async Speech

**Slug:** `MINIMAX_CREATE_ASYNC_SPEECH`

Start a long-form asynchronous MiniMax speech synthesis task from inline text or one uploaded text file.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | string | No | Inline text to synthesize, up to 50,000 characters. Supply exactly one of text or text_file_id. |
| `model` | string ("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") | Yes | Speech synthesis model. |
| `text_file_id` | string | No | Uploaded txt or zip file ID containing up to 1,000,000 characters. Supply exactly one of text_file_id or text. |
| `voice_modify` | object | No | Optional voice effects; supported only for mp3, wav, and flac output. |
| `audio_setting` | object | No | Generated audio encoding settings. |
| `voice_setting` | object | Yes | Voice and delivery settings. |
| `language_boost` | string ("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") | No | Documented language or dialect boost value, or auto for detection. |
| `pronunciation_dict` | object | No | Custom pronunciation rules. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Legacy Video

**Slug:** `MINIMAX_CREATE_LEGACY_VIDEO`

Start a MiniMax v1 Hailuo text, image, first-and-last-frame, or subject-reference video task with mode-specific validation.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `mode` | string ("text_to_video" | "image_to_video" | "first_last_frame" | "subject_reference") | Yes | Generation mode. It selects the required input and valid model family and is not sent to MiniMax. |
| `model` | string ("MiniMax-Hailuo-2.3" | "MiniMax-Hailuo-2.3-Fast" | "MiniMax-Hailuo-02" | "T2V-01-Director" | "T2V-01" | "I2V-01-Director" | "I2V-01-live" | "I2V-01" | "S2V-01") | Yes | Legacy video model supported by the selected mode. |
| `prompt` | string | No | Video prompt. Required for text_to_video and optional for the other modes. |
| `duration` | integer ("6" | "10") | No | Video duration in seconds; supported combinations use 6 or 10. |
| `resolution` | string ("512P" | "720P" | "768P" | "1080P") | No | Video resolution supported by the selected model, mode, and duration. |
| `callback_url` | string | No | HTTPS callback URL for task updates and challenge verification. |
| `last_frame_image` | string | No | Public URL or base64 image data URI for the last frame. Used only by first_last_frame. |
| `prompt_optimizer` | boolean | No | Whether MiniMax may optimize the prompt. |
| `fast_pretreatment` | boolean | No | Whether to reduce prompt optimization time; supported only by Hailuo 2.x models. |
| `first_frame_image` | string | No | Public URL or base64 image data URI for the first frame. Required by image modes. |
| `subject_reference` | array | No | Character reference used only by subject_reference mode. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create OpenAI-Compatible Response

**Slug:** `MINIMAX_CREATE_RESPONSE`

Call MiniMax through its OpenAI Responses compatibility contract and return one non-streaming response object.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | object | No | Text output configuration. |
| `input` | string | Yes | Text input or full Responses-compatible conversation history. |
| `model` | string | Yes | Model ID for the Responses-compatible request. |
| `tools` | array | No | Available function tools. |
| `top_p` | number | No | Nucleus sampling probability. |
| `stream` | boolean | No | Streaming is disabled because this action returns one JSON response. |
| `metadata` | object | No | String-valued request metadata. |
| `reasoning` | object | No | Reasoning configuration. |
| `temperature` | number | No | Sampling temperature in the interval (0, 1]. |
| `tool_choice` | string ("none" | "auto") | No | Tool selection strategy. |
| `instructions` | string | No | System instructions. |
| `service_tier` | string ("standard" | "priority") | No | Request admission tier. |
| `prompt_cache_key` | string | No | Prompt cache routing identifier. |
| `max_output_tokens` | integer | No | Maximum output tokens, including reasoning tokens. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Template Video

**Slug:** `MINIMAX_CREATE_TEMPLATE_VIDEO`

Start a MiniMax Video Agent task using an official template and its ordered text and media inputs.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `template_id` | string | Yes | Official MiniMax Video Agent template ID. |
| `text_inputs` | array | No | Text slot values in the order required by the template. |
| `callback_url` | string | No | HTTPS callback URL for task updates and challenge verification. |
| `media_inputs` | array | No | Media slot values in the order required by the template. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Video

**Slug:** `MINIMAX_CREATE_VIDEO`

Start a MiniMax H3 video v2 generation task from text and optional reference media. Returns an asynchronous task ID for MINIMAX_GET_VIDEO_TASK.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `extra` | object | No | Advanced MiniMax-H3-Max generation options, currently prompt expansion only. |
| `model` | string ("MiniMax-H3" | "MiniMax-H3-Max") | Yes | H3-family video model ID. MiniMax-H3 supports 768P and 2K; MiniMax-H3-Max supports 480P and 768P. |
| `ratio` | string ("adaptive" | "21:9" | "16:9" | "4:3" | "1:1" | "3:4" | "9:16") | No | Output aspect ratio. Text-only generation requires a concrete ratio; image-to-video uses adaptive; reference generation defaults to adaptive. |
| `content` | array | Yes | Ordered multimodal content blocks. Include a non-empty text prompt and optionally first/last-frame images or reference image, video, and audio media. Frame and reference modes cannot be mixed. |
| `duration` | integer | Yes | Output duration in seconds. MiniMax-H3 supports 4-15; MiniMax-H3-Max supports 5-15. |
| `resolution` | string ("480P" | "768P" | "2K") | Yes | Output resolution. Use 768P or 2K with MiniMax-H3, and 480P or 768P with MiniMax-H3-Max. |
| `callback_url` | string | No | HTTPS callback URL for task updates. It must answer MiniMax's challenge verification within three seconds. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Create Video Prompt

**Slug:** `MINIMAX_CREATE_VIDEO_PROMPT`

Start a MiniMax H3 Context-IR task that converts multimodal context into an enhanced video prompt.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | Yes | Context interpretation model; currently MiniMax-H3. |
| `ratio` | string ("adaptive" | "21:9" | "16:9" | "4:3" | "1:1" | "3:4" | "9:16") | No | Intended aspect ratio. Text-only input requires a concrete ratio. |
| `content` | array | Yes | Prompt plus optional frame or reference media used to produce an enhanced prompt. |
| `duration` | integer | Yes | Intended video duration in seconds, from 4 through 15. |
| `callback_url` | string | No | HTTPS callback URL for task updates and challenge verification. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete File

**Slug:** `MINIMAX_DELETE_FILE`

Permanently delete one MiniMax file by its exact ID and storage-purpose category. This operation cannot be undone.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file_id` | string | Yes | Exact MiniMax file ID to permanently delete. Numeric IDs are accepted and preserved as strings at the tool boundary. |
| `purpose` | string ("voice_clone" | "prompt_audio" | "t2a_async" | "t2a_async_input" | "video_generation") | Yes | Purpose category under which MiniMax stores the file. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Cancel or Delete Video Task

**Slug:** `MINIMAX_DELETE_VIDEO_TASK`

Cancel a queued MiniMax video v2 task, or permanently delete a completed or failed task record. The operation performed depends on the task's current state.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | Video v2 task ID to cancel if the task is queued, or permanently delete if the task has completed or failed. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Delete Voice

**Slug:** `MINIMAX_DELETE_VOICE`

Permanently delete an eligible MiniMax cloned or designed voice.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_id` | string | Yes | ID of the cloned or generated voice to permanently delete. |
| `voice_type` | string ("voice_cloning" | "voice_generation") | Yes | Deletable voice category: cloned or generated voice. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Design Voice

**Slug:** `MINIMAX_DESIGN_VOICE`

Design a reusable MiniMax voice from a description and return its paid preview as a downloadable audio file.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `prompt` | string | Yes | Natural-language description of the voice to design. |
| `voice_id` | string | No | Optional custom voice ID; MiniMax generates one when omitted. |
| `preview_text` | string | Yes | Text spoken in the paid preview audio, up to 500 characters. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Download File

**Slug:** `MINIMAX_DOWNLOAD_FILE`

Download the binary contents of one generated MiniMax file and return a managed file reference. Response headers determine the original name and MIME type when available; downloads larger than 100 MB are rejected.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file_id` | string | Yes | Exact ID of the generated MiniMax file to download. Numeric IDs are accepted and preserved as strings. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Estimate Responses Input Tokens

**Slug:** `MINIMAX_ESTIMATE_RESPONSE_INPUT_TOKENS`

Estimate input tokens using MiniMax's OpenAI Responses compatibility contract without generating model output.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | object | No | Text output configuration included in the estimate. |
| `input` | string | Yes | Text input or full Responses-compatible conversation history. |
| `model` | string | Yes | Model ID whose Responses-compatible token accounting to use. |
| `tools` | array | No | Function tools included in the estimate. |
| `reasoning` | object | No | Reasoning configuration included in the estimate. |
| `tool_choice` | string ("none" | "auto") | No | Tool selection strategy. |
| `instructions` | string | No | System instructions included in the estimate. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Generate Anthropic-Compatible Message

**Slug:** `MINIMAX_GENERATE_ANTHROPIC_MESSAGE`

Call MiniMax through its Anthropic Messages compatibility contract and return one non-streaming message response.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string ("MiniMax-M3.1-Flash-Preview" | "MiniMax-M3" | "MiniMax-M2.7" | "MiniMax-M2.7-highspeed" | "MiniMax-M2.5" | "MiniMax-M2.5-highspeed" | "MiniMax-M2.1" | "MiniMax-M2.1-highspeed" | "MiniMax-M2") | Yes | Model ID for the Anthropic-compatible request. |
| `tools` | array | No | Available Anthropic-format tools. |
| `top_p` | number | No | Nucleus sampling probability. |
| `stream` | boolean | No | Streaming is disabled because this action returns one JSON response. |
| `system` | string | No | System prompt. |
| `messages` | array | Yes | Conversation messages in Anthropic format. |
| `metadata` | object | No | Request metadata. |
| `thinking` | object | No | Thinking configuration. |
| `max_tokens` | integer | No | Maximum generated tokens. |
| `temperature` | number | No | Sampling temperature from 0 to 2. |
| `tool_choice` | object | No | Tool selection configuration. |
| `service_tier` | string ("standard" | "priority") | No | Request admission tier. |
| `output_config` | object | No | Output and thinking-depth settings. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Generate Image

**Slug:** `MINIMAX_GENERATE_IMAGE`

Generate one or more images from a text prompt, optionally guided by a subject reference.

**Instant:** Supported on the latest version.

**Instant pricing:** $0.350 per 100 successfully generated image-01 images.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `seed` | integer | No | Random seed. Reusing a seed with the same parameters helps reproduce an image. |
| `model` | string ("image-01" | "image-01-live") | Yes | Image generation model ID. |
| `width` | integer | No | Output width in pixels (512-2,048, divisible by 8). Must be supplied with height. |
| `height` | integer | No | Output height in pixels (512-2,048, divisible by 8). Must be supplied with width. |
| `prompt` | string | Yes | Detailed description of the image to generate (1-1,500 characters). |
| `image_count` | integer | No | Number of images to generate (1-9). |
| `aspect_ratio` | string ("1:1" | "16:9" | "4:3" | "3:2" | "2:3" | "3:4" | "9:16" | "21:9") | No | Preset output aspect ratio. If supplied with width and height, this preset takes priority. |
| `response_format` | string ("url" | "base64") | No | Return temporary image URLs or base64-encoded image data. URLs expire after 24 hours. |
| `prompt_optimizer` | boolean | No | Whether MiniMax may automatically optimize the prompt before generation. |
| `subject_reference` | array | No | Character portrait references for image-guided generation. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Generate Native Chat Completion

**Slug:** `MINIMAX_GENERATE_NATIVE_CHAT_COMPLETION`

Call MiniMax's native chatcompletion_v2 contract and return one non-streaming completion, including native sensitivity metadata.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string ("MiniMax-M3.1-Flash-Preview" | "MiniMax-M3" | "MiniMax-M2.7" | "MiniMax-M2.7-highspeed" | "MiniMax-M2.5" | "MiniMax-M2.5-highspeed" | "MiniMax-M2.1" | "MiniMax-M2") | Yes | Model ID accepted by the native chatcompletion_v2 contract. |
| `tools` | array | No | Available function tools. |
| `top_p` | number | No | Nucleus sampling probability in the interval (0, 1]. |
| `stream` | boolean | No | Streaming is disabled because this action returns one JSON response. |
| `messages` | array | Yes | Conversation messages in MiniMax's native chat format. |
| `max_tokens` | integer | No | Deprecated maximum generated tokens. |
| `temperature` | number | No | Sampling temperature in the interval (0, 1]. |
| `tool_choice` | string ("none" | "auto") | No | Tool selection strategy. |
| `stream_options` | object | No | Streaming options retained for contract compatibility; stream is forced off. |
| `response_format` | object | No | Structured output format for supported models. |
| `mask_sensitive_info` | boolean | No | Whether to mask sensitive information in output. |
| `max_completion_tokens` | integer | No | Maximum generated tokens. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Generate Text

**Slug:** `MINIMAX_GENERATE_TEXT`

Generate one non-streaming OpenAI-compatible chat completion, including optional reasoning and tool calls.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | Yes | Text model ID; use MINIMAX_LIST_TEXT_MODELS to discover currently available IDs. |
| `tools` | array | No | Function tools the model may call, using OpenAI-compatible tool definitions. |
| `top_p` | number | No | Nucleus-sampling probability mass from 0 through 1. |
| `messages` | array | Yes | Conversation messages in OpenAI chat format, each with a role and text or multimodal content. |
| `thinking` | object | No | Thinking configuration for models that support selecting a mode. |
| `temperature` | number | No | Sampling temperature from 0 through 2; higher values increase randomness. |
| `reasoning_effort` | string ("low" | "medium" | "high" | "xhigh" | "max") | No | Reasoning effort for supported models: low, medium, high, xhigh, or max. |
| `max_completion_tokens` | integer | No | Maximum completion tokens; allow enough room for reasoning because a small value can end before visible output. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Anthropic-Compatible Model

**Slug:** `MINIMAX_GET_ANTHROPIC_MODEL`

Retrieve one MiniMax text model through the Anthropic Models compatibility contract.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model_id` | string | Yes | Anthropic-compatible model identifier. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Async Speech Task

**Slug:** `MINIMAX_GET_ASYNC_SPEECH_TASK`

Get the status and generated file reference for a MiniMax asynchronous speech synthesis task.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | Async speech task ID returned by CREATE_ASYNC_SPEECH, as a decimal string. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get File

**Slug:** `MINIMAX_GET_FILE`

Retrieve metadata for one MiniMax file by its exact ID, including a temporary download URL when MiniMax provides one for a generated output.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file_id` | string | Yes | Exact MiniMax file ID returned by upload, video generation, or async speech synthesis. Numeric IDs are accepted and preserved as strings. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Legacy Video Task

**Slug:** `MINIMAX_GET_LEGACY_VIDEO_TASK`

Get the status and output file metadata of a MiniMax v1 legacy video task.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | Legacy task ID returned by MINIMAX_CREATE_LEGACY_VIDEO. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Template Video Task

**Slug:** `MINIMAX_GET_TEMPLATE_VIDEO_TASK`

Get the status and temporary result URL of a MiniMax Video Agent template task.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | Template task ID returned by MINIMAX_CREATE_TEMPLATE_VIDEO. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get OpenAI-Compatible Text Model

**Slug:** `MINIMAX_GET_TEXT_MODEL`

Retrieve one MiniMax text model through the OpenAI Models compatibility contract.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model_id` | string | Yes | OpenAI-compatible model identifier. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Video Task

**Slug:** `MINIMAX_GET_VIDEO_TASK`

Get the current state and output of one MiniMax video v2 task created within the last seven days. Failed tasks are returned as task records with error details.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `task_id` | string | Yes | Video v2 task ID returned by MINIMAX_CREATE_VIDEO or MINIMAX_LIST_VIDEO_TASKS. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Anthropic-Compatible Models

**Slug:** `MINIMAX_LIST_ANTHROPIC_MODELS`

List one page of MiniMax text models through the Anthropic Models compatibility contract, using its after_id or before_id cursors.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Number of models to return on this page. |
| `after_id` | string | No | Return models after this model ID. |
| `before_id` | string | No | Return models before this model ID. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Files

**Slug:** `MINIMAX_LIST_FILES`

List MiniMax files for one upload-purpose category. MiniMax documents no pagination for this endpoint.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `purpose` | string ("voice_clone" | "prompt_audio" | "t2a_async_input" | "video_generation_input") | Yes | Purpose category whose uploaded files should be returned. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Text Models

**Slug:** `MINIMAX_LIST_TEXT_MODELS`

List text model IDs currently available to the connected MiniMax API key.

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Video Tasks

**Slug:** `MINIMAX_LIST_VIDEO_TASKS`

List one page of MiniMax video v2 tasks from the last seven days, optionally filtered by status, task ID, model, or task type.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | No | Return only tasks created with this model ID. |
| `cursor` | string | No | Opaque continuation cursor returned by the previous call. Omit for the first page and pass it back unchanged. |
| `status` | string ("queued" | "running" | "succeeded" | "failed" | "cancelled") | No | Return only tasks in this status. |
| `task_ids` | array | No | Return only tasks with these task IDs. |
| `page_size` | integer | No | Maximum tasks to return in this page. |
| `task_type` | string ("generation" | "h3_context_ir" | "regeneration") | No | Return only tasks of this type. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### List Voices

**Slug:** `MINIMAX_LIST_VOICES`

List system, cloned, generated, or all voices that can be used for speech synthesis.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `voice_type` | string ("system" | "voice_cloning" | "voice_generation" | "all") | Yes | Voice category to return: system for built-in voices, voice_cloning for cloned voices, voice_generation for designed voices, or all to return every category in one list. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Regenerate Video

**Slug:** `MINIMAX_REGENERATE_VIDEO`

Regenerate an eligible MiniMax-H3 768P source video as a 2K video, using either its task ID or the exact original inputs and source video.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string | Yes | Regeneration model; currently MiniMax-H3. |
| `content` | array | No | Final source prompt and original generation inputs, plus exactly one video_url item whose role is base_video. Mutually exclusive with source_task_id. |
| `resolution` | string | Yes | Target regeneration resolution; currently 2K. |
| `callback_url` | string | No | HTTPS callback URL for task updates and challenge verification. |
| `aigc_watermark` | boolean | No | Whether to add an AIGC label watermark. |
| `source_task_id` | string | No | Succeeded, owned v2 generation task ID from the last seven days. Mutually exclusive with content. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Synthesize Speech

**Slug:** `MINIMAX_SYNTHESIZE_SPEECH`

Synchronously synthesize up to 9,999 characters of text and return the decoded audio as a downloadable file.

**Instant:** Supported on the latest version.

**Instant pricing:** $0.006 per 100 billable characters for speech-2.8-turbo; $0.010 per 100 billable characters for speech-2.8-hd.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `text` | string | Yes | Text to synthesize (1-9,999 characters). |
| `model` | string ("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") | Yes | Speech synthesis model to use. |
| `voice_modify` | object | No | Optional voice effects supported for non-streaming mp3, wav, and flac output. |
| `audio_setting` | object | No | Generated audio encoding settings. |
| `voice_setting` | object | Yes | Voice identity and delivery settings. |
| `language_boost` | string ("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") | No | Documented language or dialect boost value, or auto for detection; when omitted, MiniMax applies no language boost. |
| `pronunciation_dict` | object | No | Custom pronunciation rules applied simultaneously during synthesis. |
| `text_normalization_mode` | string ("basic" | "quality") | No | Text normalization mode. Quality mode adds latency and is supported only by selected models. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Transcribe Audio

**Slug:** `MINIMAX_TRANSCRIBE_AUDIO`

Transcribe an uploaded audio file with optional language hints, timestamps, speaker diarization, subtitle output, or assembled streaming output.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | Audio file to transcribe. Supported containers are WAV, AIFF, FLAC, ALAC/M4A, MP3, AAC, Opus, and OGG; maximum duration is 500 seconds and maximum size is 50 MB. |
| `model` | string | No | MiniMax speech recognition model. |
| `stream` | boolean | No | Stream incremental transcription events. Streaming supports only response_format=json; the action assembles the deltas into final text. |
| `language` | string ("" | "zh" | "yue" | "en" | "ja" | "ko" | "th" | "vi" | "id" | "ms" | "fil" | "ar" | "tr" | "fr" | "de" | "es" | "it" | "pt" | "pl" | "ru" | "uk") | No | Optional BCP-47 primary-language hint, such as en, zh, yue, ja, or es. Omit it for mixed-language recognition. |
| `response_format` | string ("json" | "verbose_json" | "srt" | "vtt") | No | Result format. json returns text and duration; verbose_json also returns speaker/timestamp segments; srt and vtt return a downloadable subtitle file. |
| `timestamp_level` | string ("" | "sentence" | "word") | No | Timestamp granularity for verbose_json, srt, or vtt. Empty or sentence uses sentence/segment timestamps; word uses character-level timestamps for Chinese and word-level timestamps for English. Ignored for json. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Upload File

**Slug:** `MINIMAX_UPLOAD_FILE`

Upload one file to MiniMax as multipart/form-data for voice cloning, async speech, video understanding, or video generation.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | Yes | File to upload. Its original name and MIME type are preserved in the multipart file part; MiniMax validates purpose-specific format and size limits. |
| `purpose` | string ("voice_clone" | "prompt_audio" | "t2a_async_input" | "video_understanding" | "video_generation_input") | Yes | MiniMax ingestion purpose. voice_clone and prompt_audio accept MP3, M4A, or WAV; t2a_async_input accepts TXT or ZIP long-text input; video_understanding accepts MP4, AVI, MOV, or MKV; video_generation_input accepts JPG/JPEG, PNG, WEBP, HEIC, or HEIF images up to 30 MB, MP4 or MOV video up to 50 MB, or WAV or MP3 audio up to 15 MB. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |