Use image and voice generation with ChatGPT and OpenAI Agents

Generate images, speak text aloud and transcribe audio from inside the agent loop. Connect ChatGPT and OpenAI Agents to the WingMan MCP gateway once and these tools are available in every conversation.

1. Connect ChatGPT and OpenAI Agents

With the OpenAI Agents SDK (Python), connect over Streamable HTTP as below. The same URL works as a remote MCP tool in the Responses API and as a custom connector in ChatGPT developer mode.

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp


async def main():
    async with MCPServerStreamableHttp(name="wingman", params={"url": "https://wingmanprotocol.com/mcp", "headers": {"X-Wingman-Tools": "full"}}) as wingman:
        agent = Agent(name="Assistant", mcp_servers=[wingman])
        result = await Runner.run(agent, "Use the wingman tools for this task.")
        print(result.final_output)


asyncio.run(main())

# Responses API instead of the SDK:
# tools=[{"type": "mcp", "server_label": "wingman", "server_url": "https://wingmanprotocol.com/mcp", "require_approval": "never"}]

2. The tools you get

Names and descriptions come straight from the live tool registry.

• gen_imageGenerate an image from a text prompt via FAL Flux.
• tts_voiceText-to-speech via ElevenLabs.
• voice_transcribeTranscribe short audio to text via OpenAI Whisper.
• gen_id_portraitFREE identity-preserving portrait: give ONE face photo (face_url or face_b64) and get a stylized portrait that keeps the person's face (Ins…

These tools sit outside the default tool list, so the config above sets X-Wingman-Tools: full to load the whole catalogue. Without it, your agent can still reach them with discover_tools, then get_tool_schema, then tools/call.

3. Ask for it

Give ChatGPT and OpenAI Agents a task that needs it, for example “use gen_image from wingman”. The tool call goes to https://wingmanprotocol.com/mcp and the result comes back into the conversation.

Image and voice generation with other clients

More tool categories for ChatGPT and OpenAI Agents