Vercel AI SDK

@lokutor/ai-sdk-provider (source) adds Lokutor to the Vercel AI SDK as a speech model and a transcription model. It targets AI SDK 7; it does not work with ai 6.

npm install ai @lokutor/ai-sdk-provider

import { experimental_generateSpeech as generateSpeech, transcribe } from "ai"; // `generateSpeech` in recent versions
import { lokutor } from "@lokutor/ai-sdk-provider";

const { audio } = await generateSpeech({
  model: lokutor.speech("versa-2.0"),
  text: "Hello, this is Lokutor.",
  voice: "F1",
  language: "en",
});

const { text } = await transcribe({
  model: lokutor.transcription("lokutor-stt"),
  audio: audio.uint8Array,
  providerOptions: { lokutor: { languageCode: "en" } },
});

Set LOKUTOR_API_KEY in the environment, or create the provider yourself with createLokutor({ apiKey }).

Behaviour to know

Speech is always WAV. outputFormat, speed and instructions are not supported and produce a warning instead of being sent.
Transcription takes WAV audio only, as the speech-to-text API does.
Speaker labels and the language are set through providerOptions.lokutor.
Voices and languages are those of the Lokutor API.

Get Started

SDK

API Reference

Resources

Behaviour to know

​Behaviour to know

Behaviour to know