Skip to main content
AssemblyAI is a text-to-speech plugin. It streams low-latency speech from one session for the whole call, in English, Spanish, German, Italian, Portuguese, and French, plus your own cloned voices.

Setup

Set your AssemblyAI API key in the worker environment. Generate a key from the AssemblyAI site:

Usage

Import the plugin and pass it to the pipeline’s tts slot.
AssemblyAITTS ships in the Python SDK only. The Node JS SDK does not include this plugin yet.
AssemblyAITTS requires a zeroruntime release newer than 0.1.9.

Parameters

Constructor parameters for AssemblyAITTS.

Import paths

Synthesized audio is streamed back to the caller after the LLM produces a response.

Inference

This provider also runs through the Inference Gateway on your Zero Runtime auth token, with no AssemblyAI API key. Import AssemblyAITTS from zeroruntime.inference instead of zeroruntime.plugins.