Skip to navigation
SDKs & Libraries

JellyPod Speech SDK

Use Smallest AI TTS in any JavaScript or TypeScript app with the JellyPod Speech SDK.
View as Markdown

Use Smallest AI as a TTS provider in the JellyPod Speech SDK - a universal, cross-platform TypeScript SDK that works in Node.js, edge runtimes, and the browser. Switch between providers without changing your application code.

Installation

npm install @speech-sdk/core

Setup

Get your API key from app.smallest.ai and set it as an environment variable:

export SMALLEST_API_KEY="your_key_here"

Models

@speech-sdk/core 0.38.0 sends every Smallest AI request, including lightning_v3.1_pro, to the legacy /lightning-v3.1/get_speech route. This works today, but that route will be retired on Nov 30, 2026. Speech through this SDK will stop working then unless the SDK moves to POST /waves/v1/tts.

The SDK supports two Lightning models:

ModelPoolLanguagesVoicesVoice Cloning
lightning_v3.1Standard15217Yes (5–15s of audio)
lightning_v3.1_proPremiumen, hiCurated catalogNo

Pass the model id to the factory to select which model to use:

const smallestAI = createSmallestAI({ apiKey: process.env.SMALLEST_API_KEY });
smallestAI()                       // lightning_v3.1 (default)
smallestAI("lightning_v3.1")       // standard pool — 15 languages, 217 voices
smallestAI("lightning_v3.1_pro")   // premium pool — curated American, British, Indian voices

Generate Speech

Add this inside any TypeScript/JavaScript file in your project - an API route, a server action, a backend script, or a CLI tool:

import { generateSpeech } from "@speech-sdk/core";
import { createSmallestAI } from "@speech-sdk/core/providers";
const smallestAI = createSmallestAI({ apiKey: process.env.SMALLEST_API_KEY });
const result = await generateSpeech({
  model: smallestAI("lightning_v3.1_pro"),
  text: "Hello from Smallest AI!",
  voice: "meher",
});
// result.audio.uint8Array  — raw bytes (write to a file or stream to a player)
// result.audio.base64      — base64 encoded audio
// result.audio.mediaType   — e.g. "audio/wav"
// result.metadata.audioDurationMs
// result.metadata.latencyMs

The createSmallestAI() factory reads SMALLEST_API_KEY from the environment automatically if no apiKey is passed.

Provider Options

All parameters are optional. Pass them via providerOptions to override defaults:

const result = await generateSpeech({
  model: smallestAI("lightning_v3.1_pro"),
  text: "Hello!",
  voice: "kaitlyn",
  providerOptions: {
    sample_rate: 24000,   // 8000 | 16000 | 24000 | 44100 (default: 44100)
    speed: 1.2,           // 0.5 – 2.0 (default: 1.0)
    language: "en",       // en, hi, mr, kn, ta, bn, gu, te, ml, pa, or, es, auto (default: en)
    output_format: "mp3", // pcm | wav | mp3 | ulaw | alaw (default: wav)
  },
});

Save to File (Node.js)

import { writeFileSync } from "fs";
const result = await generateSpeech({
  model: smallestAI("lightning_v3.1_pro"),
  text: "This will be saved to a WAV file.",
  voice: "meher",
});
writeFileSync("output.wav", result.audio.uint8Array);

Available Voices

Premium Pool (lightning_v3.1_pro)

Curated catalog with American, British, and Indian accents. Default voice: meher. Indian voices code-switch between English and Hindi; British and American voices are English-only.

const result = await generateSpeech({
  model: smallestAI("lightning_v3.1_pro"),
  text: "Hello from Pro!",
  voice: "meher",
});
AccentGenderVoices
IndianFemalerhea, zariya, kareena, mishka, inaaya, saira, meher, aarini
IndianMaleaviraj, vyom, zoravar, reyansh, ahan
BritishFemalecressida, elowen, ottilie, seraphina, tabitha, arabella
BritishMalebenedict, cormac, everett, finley, rupert, winston, caspian
AmericanFemalewillow, autumn, skylar, savannah, kennedy, reagan, sierra
AmericanMalemaverick, brooks, hunter, colton, wesley, asher

Fetch the full list:

curl "https://api.smallest.ai/waves/v1/lightning-v3.1-pro/get_voices" \
  -H "Authorization: Bearer $SMALLEST_API_KEY"

Switching Providers

One of the main benefits of the Speech SDK is swapping providers without changing application logic. To switch away from Smallest AI, replace the factory import:

// Smallest AI
import { createSmallestAI } from "@speech-sdk/core/providers";
const model = createSmallestAI()();
// OpenAI (same interface, different provider)
import { createOpenAI } from "@speech-sdk/core/providers";
const model = createOpenAI()();

Everything else - generateSpeech, result shape, metadata - stays identical.

GitHub

Speech SDK source code

npm

Install from npm

API Key

Get your Smallest AI API key

Voices

Browse and manage available voices