vaaya / catalog / media

Media APIs for AI agents

Image, video, speech and music generation and editing. 10 calls from 6 providers, each priced before it runs; provider errors are not charged.

npx @vaaya/mcp install

colors

colors/generatevaries by params

Hotel Lobby Standard (7 seconds) or Extended (29 seconds): turn 1–5 owned photo file IDs per consenting adult performer (plus an optional prompt of creative…

Deepgram

deepgram/speakvaries by params

Text-to-speech with Deepgram Aura-2

deepgram/transcribevaries by params

Transcribe audio (or the audio track of a video) to text with Deepgram Nova-3

fal

fal/generatevaries by params

Generate or edit images, video, music, and speech via fal.ai.

fal/upload1¢

Stage a media file on the fal CDN before a fal generation.

gener8ion-yung-lean-storm

gener8ion-yung-lean-storm/generatevaries by params

gener8ion yung lean storm: replace the central lead performer in the fixed 7-second Short or 29-second Extended video.

openai

openai/image-generateup to 8¢

OpenAI — generate images (/v1/images/generations, ~5¢). Params: `prompt`, optionally `model`, `size`, `n`. For most image work prefer fal (cheaper, more…

Sarvam

sarvam/speakvaries by params

Text-to-speech in Indian languages with Sarvam Bulbul

sarvam/transcribe2¢

Transcribe SHORT audio clips (under ~30 seconds) in Indian languages with Sarvam Saarika

sarvam/translate2¢

Translate text between English and 10 Indian languages (Hindi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Odia) with Sarvam

Give your agents media.

Connect Vaaya to your agent or application, then call any action on this page on your Vaaya credit.

npx @vaaya/mcp install