mixvideo-v2/cargos/text-video-agent-rust-sdk/README.md

Text Video Agent Client

A comprehensive Rust client for the Text Video Agent API - an AI content generation service that supports:

• 🎨 Image Generation - Multiple AI models (Midjourney, Stable Diffusion, etc.)
• 🎬 Video Generation - Text-to-video and image-to-video conversion
• 🎵 Audio Synthesis - Text-to-speech and voice cloning
• 💋 Lip Sync - Advanced lip synchronization with Hedra
• 🤖 Digital Human - Create and animate digital avatars
• 🧠 LLM Integration - Multi-modal AI analysis and inference
• 🔧 Workflow Automation - ComfyUI workflow execution

Features

• Type-safe API - Generated from OpenAPI 3.1 specification
• Async/await support - Built on reqwest and tokio
• Comprehensive coverage - All API endpoints included
• File upload support - Multipart form data handling
• Error handling - Structured error responses
• Documentation - Complete API documentation

Installation

Add this to your Cargo.toml:

[dependencies]
text_video_agent_client = "1.0.6"
tokio = { version = "1.0", features = ["full"] }

Quick Start

use text_video_agent_client::{apis::configuration::Configuration, apis::default_api};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = Configuration {
        base_path: "https://your-api-endpoint.com".to_string(),
        ..Default::default()
    };

    // Generate an image
    let response = default_api::submit_image_task_api_custom_image_submit_task_post(
        &config,
        // Add your parameters here
    ).await?;

    println!("Task submitted: {:?}", response);
    Ok(())
}

API Overview

This client was generated from the Text Video Agent API specification and provides access to all available endpoints:

• API version: 1.0.6
• Package version: 1.0.6
• Generated with: OpenAPI Generator 7.14.0

Documentation for API Endpoints

All URIs are relative to http://localhost

Class	Method	HTTP request	Description
DefaultApi	check_template_task_type_api_template_check_task_type_get	GET /api/template/check/task_type	检查任务类型是否可用
DefaultApi	create_higgsfield_character_api_custom_extend_higgsfield_create_character_post	POST /api/custom/extend/higgsfield/create/character	提交创建生成角色任务
DefaultApi	get_sample_prompt_api_prompt_default_get	GET /api/prompt/default	获取示例提示词
DefaultApi	get_supported_model_api_custom_extend_model_list_get	GET /api/custom/extend/model/list	获取支持的模型列表
DefaultApi	get_supported_model_api_custom_model_list_get	GET /api/custom/model/list	获取支持的模型列表
DefaultApi	handler_create_digital_api_ark_digital_create_post	POST /api/ark/digital/create	提交创建数字人任务
DefaultApi	handler_create_video_template_api_template_create_post	POST /api/template/create	创建新的视频模板
DefaultApi	handler_delete_video_template_api_template_delete_template_id_delete	DELETE /api/template/delete/{template_id}	删除视频模板
DefaultApi	handler_higgsfield_submit_task_api_custom_extend_higgsfield_submit_task_post	POST /api/custom/extend/higgsfield/submit/task	higgsfield Soul（文生图片）模型
DefaultApi	handler_submit_generate_video_api_ark_digital_video_submit_task_post	POST /api/ark/digital/video/submit/task	生成数字人视频
DefaultApi	handler_update_video_template_api_template_update_put	PUT /api/template/update	更新视频模板
DefaultApi	health_check_api_file_health_get	GET /api/file/health	健康检测
DefaultApi	health_check_api_prompt_health_get	GET /api/prompt/health	健康检测
DefaultApi	query_frame_task_status_api_custom_extend_frame_task_status_get	GET /api/custom/extend/frame/task/status	查询首尾帧任务状态
DefaultApi	query_higgsfield_character_status_api_custom_extend_higgsfield_character_status_post	POST /api/custom/extend/higgsfield/character/status	查询创建角色状态
DefaultApi	query_higgsfield_task_status_api_custom_extend_higgsfield_task_status_get	GET /api/custom/extend/higgsfield/task/status	higgsfield 查询任务执行状态
DefaultApi	query_task_status_api_ark_digital_task_status_get	GET /api/ark/digital/task/status	查询任务状态
DefaultApi	query_task_status_api_custom_task_status_get	GET /api/custom/task/status	Query Task Status
DefaultApi	query_video_template_v2_api_template_default_get	GET /api/template/default	获取视频模板列表
DefaultApi	submit_frame_video_task_api_custom_extend_frame_submit_task_post	POST /api/custom/extend/frame/submit/task	【首尾帧生成视频】
DefaultApi	submit_image_task_api_custom_image_submit_task_post	POST /api/custom/image/submit/task	提交图片生成任务
DefaultApi	submit_video_task_api_custom_video_submit_task_post	POST /api/custom/video/submit/task	提交视频生成任务
DefaultApi	upload_file2cloud_api_ark_digital_url2vid_post	POST /api/ark/digital/url2vid	【异步】上传视频生成视频云id, 仅仅支持mp4格式的视频,视频时长较时时,建议使用链接
DefaultApi	upload_file_api_file_upload_post	POST /api/file/upload	上传文件到COS
DefaultApi	upload_s3_api_file_upload_s3_post	POST /api/file/upload/s3	上传文件到s3【推荐 cdn加速】
ApiApi	get_voices_hl_api302_hl_router_sync_get_voices_get	GET /api/302/hl_router/sync/get/voices	查询克隆的音色ID, 【接口来自官方， 302没有对应的中转接口】
ApiApi	hl_tts_api302_hl_router_sync_generate_speech_post	POST /api/302/hl_router/sync/generate/speech	海螺同步生成音频
ApiApi	upload_material_file_api302_hl_router_sync_file_upload_post	POST /api/302/hl_router/sync/file/upload	上传素材到302ai,用于复刻
ApiApi	voice_clone_api302_hl_router_sync_voice_clone_post	POST /api/302/hl_router/sync/voice/clone	声音克隆
ApiApi	async_gen_video_api_jm_async_generate_video_post	POST /api/jm/async/generate/video	异步生成视频,提交任务
ApiApi	async_query_video_status_api_jm_async_query_status_get	GET /api/jm/async/query/status	异步查询生成视频的任务状态
ApiApi	generate_video_api_api_jm_generate_video_post	POST /api/jm/generate-video	生成视频
ApiApi	get_task_status_v2_api_task_status_task_id_get	GET /api/task/status/{task_id}	异步查询任务状态
ApiApi	health_check_api_jm_health_get	GET /api/jm/health	健康检查
ApiApi	health_check_api_task_health_get	GET /api/task/health	健康检测
ApiApi	submit_task_v2_api_task_create_task_post	POST /api/task/create/task	新版异步提交任务）
ApiApi	submit_task_v3_api_task_create_task_v2_post	POST /api/task/create/task/v2	新版本异步提交任务
ApiApi	sync_generate_video_v2_api_jm_sync_generate_video_post	POST /api/jm/sync/generate/video	同步:生成视频v2,支持通过图片文件生成视频
Class302Api	fetch_supported_model_api_union_img_model_list_get	GET /api/union/img/model/list	获取支持的模型列表
Class302Api	fetch_supported_model_api_union_video_model_list_get	GET /api/union/video/model/list	获取支持的模型列表
Class302Api	query_task_status_api_union_video_async_task_id_status_get	GET /api/union/video/async/{task_id}/status	异步查询任务状态
Class302Api	submit_task_api_union_video_async_generate_video_post	POST /api/union/video/async/generate/video	异步提交任务
Class302Api	sync_gen_image_api_union_img_sync_generate_image_post	POST /api/union/img/sync/generate/image	生图
Class302aiApiApi	async_gen_video_api302_jm_async_generate_video_post	POST /api/302/jm/async/generate/video	异步生成视频,提交任务
Class302aiApiApi	async_query_video_status_api302_jm_async_query_status_get	GET /api/302/jm/async/query/status	异步查询生成视频的任务状态
Class302aiApiApi	sync_generate_video_v2_api302_jm_sync_generate_video_post	POST /api/302/jm/sync/generate/video	【302ai】同步:生成视频v2,支持通过图片文件生成视频
Class302aiMidjourneyApi	async_gen_image_api302_mj_async_generate_image_post	POST /api/302/mj/async/generate/image	异步提交生图任务
Class302aiMidjourneyApi	async_query_status_api302_mj_async_query_status_get	GET /api/302/mj/async/query/status	异步查询任务状态
Class302aiMidjourneyApi	async_query_task_status_api302_mj_video_async_task_status_post	POST /api/302/mj/video/async/task/status	异步查询生成任务进度
Class302aiMidjourneyApi	cancel_task_api302_mj_task_cancel_post	POST /api/302/mj/task/cancel	取消任务
Class302aiMidjourneyApi	desc_img_by_file_api302_mj_sync_file_img_describe_post	POST /api/302/mj/sync/file/img/describe	通过文件获取生图的提示词
Class302aiMidjourneyApi	describe_image_api_api302_mj_sync_img_describe_post	POST /api/302/mj/sync/img/describe	获取图像描述
Class302aiMidjourneyApi	generate_image_sync_api302_mj_sync_image_post	POST /api/302/mj/sync/image	同步生成图片接口
Class302aiMidjourneyApi	submit_task_api302_mj_video_async_submit_post	POST /api/302/mj/video/async/submit	异步提交生成视频任务
Class302aiMidjourneyApi	sync_gen_video_api302_mj_video_sync_generate_video_post	POST /api/302/mj/video/sync/generate/video	同步生成视频【text+img-->video】
Class302aiVeoApi	get_task_status_api302_veo_video_task_task_id_get	GET /api/302/veo/video/task/{task_id}	异步: 获取任务执行状态
Class302aiVeoApi	submit_iv_submit_api302_veo_video_async_submit_post	POST /api/302/veo/video/async/submit	异步:text-->video or text + img --> video
Class302aiVeoApi	sync_img2video_api302_veo_video_sync_generate_video_post	POST /api/302/veo/video/sync/generate/video	同步: 生成视频【文本+图片 OR 文生成视频】
ComfyuiApi	get_running_node_api_comfy_fetch_running_node_get	GET /api/comfy/fetch/running/node	根据任务数,获取运行节点
ComfyuiApi	query_task_status_api_comfy_async_task_status_get	GET /api/comfy/async/task/status	查询任务状态
ComfyuiApi	submit_task_api_comfy_async_submit_task_post	POST /api/comfy/async/submit/task	异步提交任务
ComfyuiApi	sync_execute_workflow_api_comfy_sync_execute_workflow_post	POST /api/comfy/sync/execute/workflow	同步执行comfy工作流
DefaultApi	root_get	GET /	Root
Hedra20Api	internal_upload_file_api302_hedra_v2_upload_post	POST /api/302/hedra/v2/upload	上传文件到hedra服务器仅支持,image, audio
Hedra20Api	query_task_status_api302_hedra_v2_task_status_get	GET /api/302/hedra/v2/task/status	查询任务状态
Hedra20Api	submit_character_task_api302_hedra_v2_submit_task_post	POST /api/302/hedra/v2/submit/task	提交口型合成任务
Hedra30Api	handler_hedra_task_submit_api302_hedra_v3_submit_task_post	POST /api/302/hedra/v3/submit/task	异步提交任务
Hedra30Api	handler_query_task_status_api302_hedra_v3_task_status_get	GET /api/302/hedra/v3/task/status	查询任务状态
Hedra30Api	upload_file_to_hedra_api302_hedra_v3_file_upload_post	POST /api/302/hedra/v3/file/upload	上传文件到hedra平台,返回资源的id
LlmApi	google_file_upload	POST /api/llm/google/vertex-ai/upload	上传文件到谷歌存储,用于gemini视觉功能
LlmApi	invoke_gemini_ai_api_llm_google_chat_post	POST /api/llm/google/chat	调用google推理
LlmApi	invoke_media_analysis_api_llm_google_sync_media_analysis_post	POST /api/llm/google/sync/media/analysis	【同步适合小文件】gemini多模态分析,支持视频,音频,图片
LlmApi	llm_chat	POST /api/llm/chat	调用大模型进行推理
LlmApi	llm_supported_models	GET /api/llm/model/list	获取支持的模型列表
LlmApi	llm_task_id	GET /api/llm/task/status	查询推理过程结果
LlmApi	submit_media_inference_api_llm_google_async_media_analysis_post	POST /api/llm/google/async/media/analysis	【异步适合需要长时间的推理过程】gemini多模态分析,支持视频,音频,图片
MidjourneyApi	async_gen_image_api_mj_async_generate_image_post	POST /api/mj/async/generate/image	异步提交生图任务
MidjourneyApi	async_query_status_api_mj_async_query_status_get	GET /api/mj/async/query/status	异步查询任务状态
MidjourneyApi	desc_img_by_file_api_mj_sync_file_img_describe_post	POST /api/mj/sync/file/img/describe	通过文件获取生图的提示词
MidjourneyApi	describe_image_api_api_mj_sync_img_describe_post	POST /api/mj/sync/img/describe	获取图像描述
MidjourneyApi	generate_image_api_api_mj_generate_image_post	POST /api/mj/generate-image	生成图片
MidjourneyApi	generate_image_sync_api_mj_sync_image_post	POST /api/mj/sync/image	同步生成图片接口
MidjourneyApi	health_check_api_mj_health_get	GET /api/mj/health	健康检查
MidjourneyApi	prompt_check_api_mj_prompt_check_get	GET /api/mj/prompt/check	🔥图片提示词预审
MidjourneyapiApi	async_query_task_status_api_mj_video_async_task_status_post	POST /api/mj/video/async/task/status	异步查询生成任务进度
MidjourneyapiApi	health_check_api_mj_video_health_get	GET /api/mj/video/health	健康检查
MidjourneyapiApi	submit_video_task_api_mj_video_async_submit_post	POST /api/mj/video/async/submit	异步提交生成视频任务
MidjourneyapiApi	sync_submit_task_api_mj_video_sync_gen_post	POST /api/mj/video/sync/gen	同步生成视频视频
OmniHumanApi	query_img_recognition_status_api_ark_omnihuman_task_status_get	GET /api/ark/omnihuman/task/status	查询任务状态
OmniHumanApi	submit_img_recognition_api_ark_omnihuman_img_recognition_post	POST /api/ark/omnihuman/img/recognition	提交图片检测任务,图片中是否包含人、类人、拟人等主体
OmniHumanApi	submit_video_generate_task_api_ark_omnihuman_video_submit_task_post	POST /api/ark/omnihuman/video/submit/task	提交视频生成任务

Documentation For Models

• FileUploadResponse
• HttpValidationError
• TaskRequest
• ValidationError
• ValidationErrorLocInner

Examples

Image Generation

use text_video_agent_client::{apis::configuration::Configuration, apis::default_api};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = Configuration::default();

    // Submit image generation task
    let response = default_api::submit_image_task_api_custom_image_submit_task_post(
        &config,
        // Add your parameters
    ).await?;

    Ok(())
}

Video Generation

use text_video_agent_client::{apis::configuration::Configuration, apis::default_api};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = Configuration::default();

    // Submit video generation task
    let response = default_api::submit_video_task_api_custom_video_submit_task_post(
        &config,
        // Add your parameters
    ).await?;

    Ok(())
}

LLM Integration

use text_video_agent_client::{apis::configuration::Configuration, apis::llm_api};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let config = Configuration::default();

    // Get supported models
    let models = llm_api::llm_supported_models(&config).await?;
    println!("Available models: {:?}", models);

    Ok(())
}

API Categories

The client provides access to the following API categories:

• DefaultApi - Core functionality (templates, file upload, health checks)
• ApiApi - Task management and basic operations
• Class302Api - 302AI integration services
• Class302aiApiApi - 302AI JiMeng video generation
• Class302aiMidjourneyApi - 302AI Midjourney integration
• Class302aiVeoApi - 302AI VEO video generation
• ComfyuiApi - ComfyUI workflow execution
• Hedra20Api - Hedra 2.0 lip sync services
• Hedra30Api - Hedra 3.0 lip sync services
• LlmApi - Large Language Model integration
• MidjourneyApi - Midjourney image generation
• MidjourneyapiApi - Midjourney video generation
• OmniHumanApi - Digital human services

Documentation

To access the complete API documentation:

cargo doc --open

Or visit docs.rs/text_video_agent_client

Contributing

This client is auto-generated from the OpenAPI specification. For issues related to the API itself, please contact the API provider. For issues with this Rust client, please open an issue in the repository.

License

Licensed under either of

• Apache License, Version 2.0 (LICENSE-APACHE or http://www.apache.org/licenses/LICENSE-2.0)
• MIT license (LICENSE-MIT or http://opensource.org/licenses/MIT)

at your option.

Author