Maia Router

Interact with Maia Router API for AI model routing

Actions6

Chat Actions
- Message a model
Audio Actions
- Generate audio
- Transcribe audio
Video Actions
- Generate Video
Image Actions
- Generate image
- Edit Image

Audio → Generate audio

AI-generated

Summary

Generates speech from input text using a selected TTS model, voice, and optional response format and speed.

Inputs

Input Text (required) — The text to synthesize. Maximum 4096 characters.
Model (required) — TTS model to use. Options: OpenAI GPT-4o Mini TTS, OpenAI TTS-1, OpenAI TTS-1 HD, Gemini 2.5 Pro Preview TTS.
Voice (required) — Voice to use. Options: alloy, echo, fable, onyx, nova, shimmer.
Additional Fields — Optional response_format (mp3, opus, aac, flac, wav, pcm; default mp3) and speed (0.25–4, default 1).

Output shape

The audio generated by the API in the requested response format (default MP3). The node returns the API response as the item data.

The operation processes each input item independently. If the API call fails and 'Continue on Fail' is enabled, the node returns an error object with the error message and a pairedItem reference. The exact structure of the returned audio data is determined by the Maia Router API response.

Discussion