Aniwaffle by Narya.ai
Generate expressive speech.
Aniwaffle is Narya.ai’s Text to Speech platform. Choose a ready-made voice or clone your own, then generate audio in the Dashboard, from the CLI, or through the HTTP and WebSocket API. Every guide below starts from a fresh workspace.
Choose your path
What are you building?
Pick the closest outcome. You can move between them at any time.
Generate speech
Use a ready-made voice or clone your own, then generate audio through the API.
Dashboard first, API when you need it.
TTS APIStream speech in real time
Pick a voice, send text over HTTP or WebSocket, and play audio as it arrives.
Five-minute quickstart with runnable examples.
CLIWork from your terminal
Sign in once, then list voices, generate speech, and create API keys from a terminal or a trusted coding agent.
Requires Node.js 20.3 or newer.
Developers
Build with code
Call the TTS API from your own server. Credentials come from the Dashboard; the authentication guide shows every step.
HTTP quickstart
List voices, then turn complete text into one audio file with a single request.
POST /v1/ttsTTS APIStream over WebSocket
Send text as it arrives and play audio chunks before generation finishes.
/v1/tts/streamTTS APIAPI keys
Create a workspace key in the Dashboard and keep it on your backend.
awp_Platform boundary
Built for server-side speech
API keys stay on your server
Permanent workspace keys belong in your backend. Browsers and mobile apps receive short-lived stream tokens instead.
Streaming is built in
Send complete text over HTTP, or stream text over WebSocket and play audio while it is still being generated.
Your voices, ready-made or cloned
Use a ready-made voice or clone one from recordings you have permission to use, then request it by its voice ID.