MiniMax for AI agents
Agents read MiniMax at once. Changes and sends are held for a person's approval by default.
About MiniMax
MiniMax provides multimodal AI APIs for text, video, speech, image, music, and file workflows.
What an agent can do in MiniMax
Every MiniMax action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.
Runs at once (reads)
Looks things up in MiniMax without asking first. 10 actions.
- Download FileDownload 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
- Get Async Speech TaskGet the status and generated file reference for a MiniMax asynchronous speech synthesis task.
- Get FileRetrieve metadata for one MiniMax file by its exact ID, including a temporary download URL when MiniMax provides one for a generated output.
- Get Legacy Video TaskGet the status and output file metadata of a MiniMax v1 legacy video task.
- Get Template Video TaskGet the status and temporary result URL of a MiniMax Video Agent template task.
- Get Video TaskGet 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.
- List FilesList MiniMax files for one upload-purpose category. MiniMax documents no pagination for this endpoint.
- List Text ModelsList text model IDs currently available to the connected MiniMax API key.
- List Video TasksList one page of MiniMax video v2 tasks from the last seven days, optionally filtered by status, task ID, model, or task type.
- List VoicesList system, cloned, generated, or all voices that can be used for speech synthesis.
Held for approval by default (changes and sends)
Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 16 actions.
- Clone VoiceCreate a reusable MiniMax cloned voice from an uploaded voice sample, optionally generating paid preview audio.
- Create Async SpeechStart a long-form asynchronous MiniMax speech synthesis task from inline text or one uploaded text file.
- Create Legacy VideoStart a MiniMax v1 Hailuo text, image, first-and-last-frame, or subject-reference video task with mode-specific validation.
- Create Template VideoStart a MiniMax Video Agent task using an official template and its ordered text and media inputs.
- Create VideoStart a MiniMax H3 video v2 generation task from text and optional reference media. Returns an asynchronous task ID for MINIMAX_GET_VIDEO_TASK.
- Create Video PromptStart a MiniMax H3 Context-IR task that converts multimodal context into an enhanced video prompt.
- Delete FilePermanently delete one MiniMax file by its exact ID and storage-purpose category. This operation cannot be undone.
- Cancel or Delete Video TaskCancel 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.
- Delete VoicePermanently delete an eligible MiniMax cloned or designed voice.
- Design VoiceDesign a reusable MiniMax voice from a description and return its paid preview as a downloadable audio file.
- Generate ImageGenerate one or more images from a text prompt, optionally guided by a subject reference.
- Generate Native Chat CompletionCall MiniMax's native chatcompletion_v2 contract and return one non-streaming completion, including native sensitivity metadata.
Show all 16
- Regenerate VideoRegenerate an eligible MiniMax-H3 768P source video as a 2K video, using either its task ID or the exact original inputs and source video.
- Synthesize SpeechSynchronously synthesize up to 9,999 characters of text and return the decoded audio as a downloadable file.
- Transcribe AudioTranscribe an uploaded audio file with optional language hints, timestamps, speaker diarization, subtitle output, or assembled streaming output.
- Upload FileUpload one file to MiniMax as multipart/form-data for voice cloning, async speech, video understanding, or video generation.
Changes wait in Needs you
Changes and sends in MiniMax are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
MiniMax questions
Can an agent change data in MiniMax on its own?
Not by default. Changes and sends in MiniMax are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
What can an agent read in MiniMax?
This connector lists 10 read actions. Reads run at once, without waiting for approval.
How does MiniMax connect?
It connects with API key. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.