We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
assemblyai/assemblyai-tts-1Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
AssemblyAI TTS 1 is a text-to-speech model from AssemblyAI, listed on api14 under the model id assemblyai/assemblyai-tts-1. It sits in the speech category and is built around converting written text into spoken audio. AssemblyAI positions it for voice agents, narration, and multilingual applications, and it draws on a public library of several thousand voices. If your product needs a synthetic voice rather than text output, this is the model family to look at.
The model takes text as its input and returns speech as its output. That is the whole pipeline: you send text, you get audio back. It does not accept audio or images on the way in, and it does not return text on the way out. The context window is not specified for this model, so plan your requests around the text you actually need spoken rather than assuming a particular token budget. The provider description highlights multilingual use, which means the same model can serve applications that need more than one language, and the voice library gives you room to pick a voice that fits the product.
The use cases follow directly from that shape. Voice agents are the clearest fit: an assistant that answers spoken replies needs a text-to-speech step, and this model supplies it. Narration is the second: turning scripts, articles, or documentation into audio for listeners. Multilingual applications are the third, where the same content has to be voiced in several languages without switching to a different provider for each one. Anywhere you have text and need audio, this model is a candidate.
You call it through api14's OpenAI-compatible API, using the model id assemblyai/assemblyai-tts-1 in the same request format you would use for other models on the gateway. Because the interface follows the OpenAI convention, existing client libraries and code that already talk to an OpenAI-compatible endpoint can point at api14 and select this model without a rewrite. The model does not list any supported parameters, so treat the request as a straightforward text-in, speech-out call and avoid assuming tuning options that are not offered. Check the live price table on the page for current rates before you commit to volume.
One practical note: with no listed supported parameters and no stated context length, this model is best treated as a focused speech generator rather than a configurable one. If your task is text generation, reasoning, or anything that returns written output, a different model on api14 will fit better. If your task is turning text into a voice, this one is aimed squarely at it.
import { writeFile } from "node:fs/promises";
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const audio = await client.audio.speech.create({
"model": "assemblyai/assemblyai-tts-1",
"input": "Hello from api14! One API for every model.",
"voice": "alloy",
"response_format": "mp3"
});
await writeFile("speech.mp3", Buffer.from(await audio.arrayBuffer()));
This community has no topics yet. Open the first one about AssemblyAI: TTS 1.