18 Services from media.gedx402.com

Transcribes speech from base64-encoded audio files using the Whisper Large V3 Turbo model, paid via USDC on multiple blockchains with no API key required

Converts text to speech audio using the MeloTTS model, returning base64-encoded audio, payable with USDC via x402 protocol

Generates a natural language caption or answers a question about a provided image using the LLaVA-1.5-7B multimodal vision-language model, paid via USDC on-chain with no API key required.

Converts input text to speech audio using the Aura-1 model, returning base64-encoded audio, paid per-call with USDC via x402 protocol.

Runs Meta's Llama Guard 3 8B safety classifier on a conversation to detect unsafe or harmful content categories

Transcribes English audio to text using the Whisper Tiny EN model, paid per-call with USDC via x402 protocol — no API key required.

Detects and localizes objects in an image using the DETR ResNet-50 model, returning bounding boxes, labels, and confidence scores

Runs the Llama 3.2 11B multimodal vision model on a base64-encoded image, answering questions or following instructions about its contents

Transcribes base64-encoded audio files to text using the Nova-3 ASR model, payable with USDC on multiple blockchains via x402 protocol

Generates a natural language caption or answer from a base64-encoded image using the UForm-Gen2-Qwen-500M vision-language model, payable via USDC on multiple chains with no API key required.

Converts text to speech audio using the Aura-2 English TTS model, paid per-call in USDC via x402 protocol with no API keys required.

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

Runs AI-powered content moderation on a conversation, returning a safety verdict and flagged categories, paid per-call with USDC via x402.

Transcribes audio to text using streaming ASR, accepting linear16 PCM audio via GET request and returning turn-based speech events with transcripts

Creates a prepaid voice session with TTS, ASR, and chat credits funded via a single x402 USDC micropayment — returns session token and route endpoints for a full voice loop.

Transcribes speech from base64-encoded audio using a smart turn detection model, payable with USDC on multiple chains and requiring no API key

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

Transcribes audio content (base64-encoded WAV/MP3/etc.) into text using AI, payable per-call with USDC on multiple blockchains