What makes ControlFoley Audio Generator notable?

1.2K downloads. Trust evidence available

How should ControlFoley Audio Generator be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

ControlFoley Audio Generator

A multi-functional audio generation tool for SFX generation, video-to-audio and text-to-audio. 多功能音频生成工具，集成可控视频生成音频、文本生成音频等功能. Skill: ControlFoley Audio Generator Owner: yjx-research Summary: A multi-functional audio generation tool for SFX generation, video-to-audio and text-to-audio. 多功能音频生成工具，集成可控视频生成音频、文本生成音频等功能. Tags: latest:1.0.9 Version history: v1.0.9 | 2026-06-08T03:51:10.695Z | user - Removed the _meta.json file from the skill package. - No functional changes to user experience or features. - Internal metadata cleanup for this vers

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 11, 2026

Version

1.0.9

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.9release · observed Jun 8, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s1735syvcp8qrc0r38n7crw4pn859fn6:controlfoley-audio-generator

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-yjx-research-controlfoley-audio-generator/snapshot"

Documentation

CLAWHUB

126,313 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: controlfoley-audio-generator
description: >
  A multi-functional audio generation tool for SFX generation, video-to-audio and text-to-audio.
  多功能音频生成工具，集成可控视频生成音频、文本生成音频等功能.

---

# ControlFoley Audio Generator

A multi-functional audio generation tool powered by the ControlFoley model, integrating video sound effect (SFX) generation, video background music composition, text-to-audio and other functions to realize diversified creative audio generation. 

This tool supports four modes: Video-to-Audio (V2A), Text-Controlled Video-to-Audio (TC-V2A), Audio-Controlled Video-to-Audio (AC-V2A), and Text-to-Audio (T2A).

## Basic Info

| Field | Value |
|---|---|
| Service Operator | Xiaomi LLM Plus Team |
| API Endpoint | `https://controlfoley.ai.xiaomi.com` |
| Open Source Repo | `https://github.com/xiaomi-research/controlfoley` |
| Project Page | `https://yjx-research.github.io/ControlFoley_web_page/` |
| Online Demo | `https://yjx-research.github.io/ControlFoley_web_page/#try-gen` |
| Model Weights | `https://huggingface.co/YJX-Xiaomi/ControlFoley/` |
| API Key | Not required |
| Script Path | `scripts/foley.py` |

## Prerequisites

```bash
python3 --version   # Python 3.x
curl --version      # curl for API submission
ffmpeg -version     # optional, for audio format conversion
```

## Modes

| Mode | Command | Input | Output | Description |
|------|---------|-------|--------|-------------|
| **V2A** | `v2a video.mp4` | Video file | .mp4 + .flac | Generate audio matching the video content |
| **TC-V2A** | `v2a video.mp4 --prompt "text"` | Video + text | .mp4 + .flac | Generate audio aligned with text prompts while staying synchronized with the video |
| **AC-V2A** | `v2a video.mp4 --ref-audio ref.wav` | Video + reference audio | .mp4 + .flac | Generate audio with timbre matching reference audio while staying synchronized with the video |
| **T2A** | `t2a "prompt"` | Text description | .flac | Generate audio from text descriptions |


## Usage (CLI version)

### 1. Text-to-Audio (T2A, default 8s)

```bash
python3 scripts/foley.py t2a "dog barking loudly in a park"
```

### 2. Video-to-Audio (V2A)

```bash
python3 scripts/foley.py v2a input.mp4
```

### 3. Text-Controlled Video-to-Audio (TC-V2A)

```bash
python3 scripts/foley.py v2a input.mp4 --prompt "footsteps on gravel with birds chirping"
```

### 4. Audio-Controlled Video-to-Audio (AC-V2A)

```bash
python3 scripts/foley.py v2a input.mp4 --ref-audio reference.wav
```

### 5. Specify duration

```bash
python3 scripts/foley.py t2a "A mountain stream murmurs, its gentle current lapping against the pebbles." --duration 15
```

### 6. Generate multiple candidates

```bash
python3 scripts/foley.py t2a "cat purring softly" --count 3
```

### 7. Fixed seed (reproducible results)

```bash
python3 scripts/foley.py t2a "rain on a tin roof" --seed 42
```

### 8. List available models

```bash
python3 scripts/foley.py models
```

## Usage (API version)

### POST

```bash
curl -X POST "https://controlf

_meta.json

{
  "ownerId": "kn7ftwffrk08e278sse17ktw39858t8n",
  "slug": "controlfoley-audio-generator",
  "version": "1.0.9",
  "publishedAt": 1780890670695
}

references/api-reference.md

# ControlFoley Audio Generator API Reference

Base URL: `https://controlfoley.ai.xiaomi.com`  
Auth: None required

**Known API quirks (from real testing):**
- Submit response may return either `task_id` or `taskId` (camelCase); code handles both
- Status success may return either `processed_urls` or `urls`; code checks both
- Result URLs may use internal `.xiaomi.srv` domains; use download endpoint as fallback

## Endpoints

### POST `/api/v1/v2a/submit` — Submit Task

Content-Type: `multipart/form-data`

#### T2A (Text-to-Audio)

| Param | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| prompt | string | Yes | — | Audio description (e.g. `dog barking in park`) |
| negative | string | Optional | — | What to avoid; omitted if empty |
| duration | float | Optional | `8.0` | Audio length in seconds (max 30) |
| count | int | Optional | `1` | Number of results (1–5) |
| seed | int | Optional | — | Fixed seed for reproducibility; omitted if not set |
| cfg | float | Optional | `4.5` | CFG strength |
| outdir | string | Optional | "./output" | Output directory |

#### V2A (Video-to-Audio)

| Param | Type | Required | Default | Description |
|-------|------|----------|---------|-------------|
| video | file | Yes | — | Video file (.mp4/.webm/.mov) |
| prompt | string | Optional | — | Text prompt to guide audio generation; omitted if empty |
| negative | string | Optional | — | What to avoid; omitted if empty |
| ref_audio | file | Optional | — | Reference audio for AC-V2A task; omitted if file not found |
| count | int | Optional | `1` | Number of results (1–5) |
| seed | int | Optional | — | Fixed seed for reproducibility; omitted if not set |
| cfg | float | Optional | `4.5` | CFG strength |
| outdir | string | Optional | "./output" | Output directory |

> Note: `seed` is accepted in the V2A function signature but not currently forwarded to the API.

**Response (202):**
```json
{"task_id": "uuid", "status": "pending", "queue_pos": 2, "message": "Task submitted successfully"}
```
> Note: field may appear as `taskId` (camelCase) — handle both.

### GET `/api/v1/v2a/status/{task_id}` — Poll Status

**Pending/Processing:**
```json
{"status": "pending|processing", "queue_pos": 3}
```

**Success:**
```json
{
  "status": "success", "done": true,
  "processed_urls": ["http://.../uuid.flac", "http://.../uuid.mp4"]
}
```
> Note: result URLs field may appear as `urls` — handle both `processed_urls` and `urls`.

**Failed:**
```json
{"status": "failed", "done": true, "error": "reason"}
```

### GET `/api/v1/v2a/ControlFoley_output/{task_id}/{filename}` — Download Result

Fallback download endpoint for internal URLs that are not directly accessible.  
Returns binary file stream (.flac at 44100 Hz or .mp4).

### GET `/api/v1/v2a/models` — List Models

```json
{"models": [{"name": "ControlFoley", "enabled": true}]}
```

### GET `/health` — Health Check

```json
{"status": "ok", "queue_size": 3}
```

## Models

| Model

skill-card.md

## Description:

A multi-functional audio generation tool for SFX generation, video-to-audio and text-to-audio.

This skill is ready for commercial/non-commercial use.

## Publisher:

[yjx-research](https://clawhub.ai/user/yjx-research)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and creators use this skill to generate sound effects, background audio, or Foley-style audio from text prompts, video files, and optional reference audio.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill uploads user media to a remote ControlFoley service for processing.

Mitigation: Use only non-sensitive media and validate behavior with a small test clip before broader use.

Risk: The release security summary reports flaws that can expose local files or fetch untrusted URLs during normal use.

Mitigation: Review before installing, avoid prompt, model, or negative values beginning with @ or <, and prefer a patched version with native multipart upload, download URL validation, and size limits.

Risk: Returned downloads come from service-provided URLs.

Mitigation: Treat generated downloads as untrusted files and inspect them before using them in downstream workflows.

## Reference(s):

- [ControlFoley Audio Generator API Reference](references/api-reference.md)
- [ControlFoley project page](https://yjx-research.github.io/ControlFoley_web_page/)
- [ControlFoley online demo](https://yjx-research.github.io/ControlFoley_web_page/#try-gen)
- [ControlFoley model weights](https://huggingface.co/YJX-Xiaomi/ControlFoley/)
- [ControlFoley source repository](https://github.com/xiaomi-research/controlfoley)

## Skill Output:

**Output Type(s):** [Files, Shell commands, API Calls, Guidance]

**Output Format:** [Generated audio/video files with text status output]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Produces FLAC audio and, for video-to-audio workflows, MP4 video with generated audio.]

## Skill Version(s):

1.0.9 (source: release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.