15 Services from ged-x402-media.jvalamis.workers.dev

Generates a natural-language caption or answer for a given image using the UForm-Gen2-Qwen-500M vision-language model, paid via USDC on-chain with no API key required.

Transcribes audio to text using Whisper Large v3 Turbo, payable with USDC on multiple chains, no API key required

Converts text to speech audio using the Aura-1 model, returning base64-encoded audio, paid via USDC on multiple blockchains with no API key required.

Converts input text to speech audio using the Aura-2 English voice model, returning base64-encoded audio, paid per-call with USDC on multiple chains via x402.

Generates a natural language caption or answer for a given image using the LLaVA-1.5-7B vision-language model, paid via USDC on-chain

Transcribes audio (WAV, MP3, etc.) to text using the Nova-3 ASR model, paid per-call with USDC on multiple blockchains via x402, no API keys required.

Detects and localizes objects in a base64-encoded image using the DETR-ResNet-50 model, returning bounding boxes, labels, and confidence scores — paid per call with USDC via x402.

Transcribes English audio to text using Whisper Tiny EN via Cloudflare Workers AI, paid per-call with USDC on multiple chains

Analyzes a base64-encoded image and returns a natural language description using a vision AI model, paid per-call with USDC on multiple blockchains

Runs Llama 3.2 11B multimodal vision inference on a base64-encoded image, returning a natural language description or answer, paid per-call in USDC with no API key required.

Runs Llama Guard 3 8B content safety classification on a conversation, returning a safe/unsafe verdict and triggered harm categories, paid per-call with USDC on multiple blockchains.

Converts input text to synthesized speech audio (base64-encoded) using MeloTTS, paid per-call with USDC on-chain via x402 — no API key required.

Transcribes speech from base64-encoded audio using a smart turn detection model, payable with USDC on multiple blockchains via x402

Converts Spanish text to speech audio using the Aura-2-ES voice model, returning base64-encoded audio, paid via USDC on multiple blockchains with no API key required.

Transcribes base64-encoded audio files (WAV, MP3, etc.) into text using AI, paid per-call with USDC via x402 protocol on multiple blockchains