← Back to Skills Marketplace
Phaya Media API
by
boombignose
· GitHub ↗
· v1.0.2
· MIT-0
423
Downloads
0
Stars
1
Active Installs
3
Versions
Install in OpenClaw
/install phaya
Description
Use the Phaya SaaS backend to generate images, videos, audio, music, and run LLM chat completions via simple REST API calls. Use when the user wants to gener...
Usage Guidance
This skill appears to legitimately wrap a paid media-generation REST API and only needs an API key and base URL — which is proportionate. However, the published package metadata is inconsistent: the summary lists no required env vars while SKILL.md and clawhub.json clearly require PHAYA_API_KEY and PHAYA_BASE. Before enabling/installing: (1) confirm the platform will prompt you to supply PHAYA_API_KEY and PHAYA_BASE (and that the key is scoped/limited), (2) create a scoped/test API key with a small credit balance for initial testing, (3) review billing/credit rates in SKILL.md to avoid surprise charges, (4) if you want to limit risk, restrict or disable autonomous invocation for this skill until you’ve tested it, and (5) verify the PHAYA_BASE endpoint you configure is trusted (ensure it is the official host you intend). If the platform uses the incorrect top-level metadata (no required creds), the agent may fail to authenticate — ask the skill author or registry maintainer to fix the manifest inconsistency before broad use.
Capability Analysis
Type: OpenClaw Skill
Name: phaya
Version: 1.0.2
The 'phaya' skill bundle is a comprehensive integration for a media generation SaaS API, covering image, video, and audio generation. It includes detailed documentation (SKILL.md, endpoints.md) and functional Python/curl examples (examples.md) for interacting with a remote FastAPI backend. The skill correctly identifies sensitive credentials (PHAYA_API_KEY), provides explicit cost warnings regarding a credit-based billing system, and lacks any indicators of data exfiltration, unauthorized local execution, or malicious prompt injection.
Capability Assessment
Purpose & Capability
The name/description (Phaya Media API for images/video/audio/LLM) align with the instructions and examples, and the requested binaries (curl/python3) and optional tools (ffmpeg, yt-dlp) are appropriate for the described features. However, the top-level registry metadata in the provided summary claims no required env vars / primary credential while SKILL.md and clawhub.json both declare PHAYA_API_KEY and PHAYA_BASE as required — this manifest mismatch is inconsistent and may cause confusion or misconfiguration.
Instruction Scope
SKILL.md contains explicit REST call patterns, polling logic, and examples that stay within the declared purpose. It directs the agent to use PHAYA_API_KEY and PHAYA_BASE, to poll job status, and to optionally use local ffmpeg for a small subset of features. There are no instructions to read unrelated system files, harvest other env vars, or exfiltrate data to unexpected endpoints.
Install Mechanism
This is instruction-only (no install spec, no code files executed locally). That is the lowest-risk install pattern for this functionality.
Credentials
The only credentials the skill needs (per SKILL.md and clawhub.json) are PHAYA_API_KEY and PHAYA_BASE — these are proportional to a remote API integration and are justified by the service description. The concern is the packaging inconsistency: the top-level requirement summary reported 'Required env vars: none' and 'Primary credential: none', which contradicts the rest of the package. Verify which metadata the platform will enforce before enabling the skill.
Persistence & Privilege
The skill does not request always=true, has no install-time persistence, and uses normal agent invocation semantics. No elevated or system-wide privileges are requested.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install phaya - After installation, invoke the skill by name or use
/phaya - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Added detailed environment variable setup instructions, including required PHAYA_API_KEY and PHAYA_BASE variables.
- Included a "Cost Warning" section highlighting real credit usage and best practices for safe initial testing.
- Improved metadata with optional binary requirements (ffmpeg, yt-dlp) and credential descriptions.
- Clarified that some endpoints invoke local binaries, but most processing is remote.
- Updated "Quick Start" guidance for better onboarding and connectivity verification.
v1.0.1
- Clarified job status patterns: added new status categories for speech/subtitle endpoints.
- Corrected the structure of chat completions API response in code example (Phaya-GPT now returns a flat "message" dict, not "choices[0].message.content").
- Updated credit table: fixed pricing for Seedance 1.5 Pro (now listed as 2–35 credits).
- No code or behavior changes; documentation improvements only.
v1.0.0
- Initial release of the Phaya skill.
- Enables image, video, audio, music generation, and LLM chat via the Phaya SaaS backend REST API.
- Supports credit-based usage and asynchronous job/polling for media generation.
- Provides quick start examples for image, video, and chat completions.
- Documents major endpoints, authentication, and rate limits.
Metadata
Frequently Asked Questions
What is Phaya Media API?
Use the Phaya SaaS backend to generate images, videos, audio, music, and run LLM chat completions via simple REST API calls. Use when the user wants to gener... It is an AI Agent Skill for Claude Code / OpenClaw, with 423 downloads so far.
How do I install Phaya Media API?
Run "/install phaya" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Phaya Media API free?
Yes, Phaya Media API is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Phaya Media API support?
Phaya Media API is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Phaya Media API?
It is built and maintained by boombignose (@boombignose); the current version is v1.0.2.
More Skills