Supertone TypeScript Library

Summary

Supertone Public API: Supertone API is a RESTful API for using our state-of-the-art AI voice models.

SDK Installation

The SDK can be installed with either npm, pnpm, bun or yarn package managers.

NPM

npm add @supertone/supertone

PNPM

pnpm add @supertone/supertone

Bun

bun add @supertone/supertone

Yarn

yarn add @supertone/supertone zod

# Note that Yarn does not install peer dependencies automatically. You will need
# to install zod as shown above.

[!NOTE] This package is published with CommonJS and ES Modules (ESM) support.

Requirements

For supported JavaScript runtimes, please consult RUNTIMES.md.

SDK Example Usage

Example

import { Supertone } from "@supertone/supertone";

const supertone = new Supertone({
  apiKey: "<YOUR_API_KEY_HERE>",
});

async function run() {
  const result = await supertone.textToSpeech.createSpeech({
    voiceId: "<id>",
    apiConvertTextToSpeechUsingCharacterRequest: {
      text: "<value>",
      language: "ja",
    },
  });

  console.log(result);
}

run();

Authentication

Per-Client Security Schemes

This SDK supports the following security scheme globally:

| Name | Type | Scheme | | -------- | ------ | ------- | | apiKey | apiKey | API key |

To authenticate with the API the apiKey parameter must be set when initializing the SDK client instance. For example:

import { Supertone } from "@supertone/supertone";

const supertone = new Supertone({
  apiKey: "<YOUR_API_KEY_HERE>",
});

async function run() {
  const result = await supertone.textToSpeech.createSpeech({
    voiceId: "<id>",
    apiConvertTextToSpeechUsingCharacterRequest: {
      text: "<value>",
      language: "ja",
    },
  });

  console.log(result);
}

run();

Models

Supertone’s Text-to-Speech API provides multiple TTS models, each with different supported languages, available voice settings, and streaming capabilities.

Model Overview

| Model Name | Identifier | Streaming Support (stream_speech) | Voice Settings Support | | ----------------------- | --------------------- | ----------------------------------- | --------------------------------------------------------------------------------------------------------- | | SONA Speech 2 | sona_speech_2 | ❌ Not supported | Supports all Voice Settings except subharmonic_amplitude_control | | SONA Speech 2 Flash | sona_speech_2_flash | ❌ Not supported | Supports all Voice Settings except similarity, text_guidance, subharmonic_amplitude_control | | SONA Speech 1 | sona_speech_1 | ✅ Supported | Supports all Voice Settings | | Supertonic API 3 | supertonic_api_3 | ❌ Not supported | Supports only the speed setting (others are ignored) | | Supertonic API 1 | supertonic_api_1 | ❌ Not supported | Supports only the speed setting (others are ignored) |

[!NOTE] Streaming Support

Streaming TTS using the stream_speech endpoint is only available for the sona_speech_1 model.

Normalized Text Support

The normalized_text parameter is supported only with the sona_speech_2 and sona_speech_2_flash models.
It is ignored when used with other models.

Supported Languages by Model

[!NOTE] The set of supported input languages varies depending on the TTS model.

• sona_speech_2

  • en, ko, ja, bg, cs, da, el, es, et, fi, hu, it, nl, pl, pt, ro,
    ar, de, fr, hi, id, ru, vi

• sona_speech_2_flash

  • en, ko, ja, bg, cs, da, el, es, et, fi, hu, it, nl, pl, pt, ro,
    ar, de, fr, hi, id, ru, vi

• sona_speech_1

  • en, ko, ja

• supertonic_api_3

  • en, ko, ja, ar, bg, cs, da, de, el, es, et, fi, fr, hi, hr, hu,
    id, it, lt, lv, nl, pl, pt, ro, ru, sk, sl, sv, tr, uk, vi

• supertonic_api_1

  • en, ko, ja, es, pt

Voice Settings (Optional)

Some TTS models support optional voice settings that allow fine control over output speech characteristics (e.g., speed, pitch, pitch variance).

[!NOTE] The available Voice Settings vary depending on the TTS model.

• sona_speech_2

  • Supports all Voice Settings except subharmonic_amplitude_control.

• sona_speech_2_flash

  • Supports all Voice Settings except similarity, text_guidance, subharmonic_amplitude_control.

• sona_speech_1

  • Supports all available Voice Settings.

• supertonic_api_3

  • Supports only the speed setting.
    All other settings will be ignored.

• supertonic_api_1

  • Supports only the speed setting.
    All other settings will be ignored.

All Voice Settings are optional. When omitted, each model’s default values will be applied.

Error Handling

SupertoneError is the base class for all HTTP error responses. It has the following properties:

| Property | Type | Description | | ------------------- | ---------- | --------------------------------------------------------------------------------------- | | error.message | string | Error message | | error.statusCode | number | HTTP response status code eg 404 | | error.headers | Headers | HTTP response headers | | error.body | string | HTTP body. Can be empty string if no body is returned. | | error.rawResponse | Response | Raw HTTP response | | error.data$ | | Optional. Some errors may contain structured data. See Error Classes. |

Example

import { Supertone } from "@supertone/supertone";
import * as errors from "@supertone/supertone/models/errors";

const supertone = new Supertone({
  apiKey: "<YOUR_API_KEY_HERE>",
});

async function run() {
  try {
    const result = await supertone.textToSpeech.createSpeech({
      voiceId: "<id>",
      apiConvertTextToSpeechUsingCharacterRequest: {
        text: "<value>",
        language: "ja",
      },
    });

    console.log(result);
  } catch (error) {
    // The base class for HTTP error responses
    if (error instanceof errors.SupertoneError) {
      console.log(error.message);
      console.log(error.statusCode);
      console.log(error.body);
      console.log(error.headers);

      // Depending on the method different errors may be thrown
      if (error instanceof errors.BadRequestErrorResponse) {
        console.log(error.data$.status); // string
        console.log(error.data$.message); // string
      }
    }
  }
}

run();

Error Classes

Primary error:

• SupertoneError: The base class for HTTP error responses.

Network errors:

• ConnectionError: HTTP client was unable to make a request to a server.
• RequestTimeoutError: HTTP request timed out due to an AbortSignal signal.
• RequestAbortedError: HTTP request was aborted by the client.
• InvalidRequestError: Any input used to create a request is invalid.
• UnexpectedClientError: Unrecognised or unexpected error.

Inherit from SupertoneError:

• UnauthorizedErrorResponse: Unauthorized: Invalid API key. Status code 401. Applicable to 10 of 15 methods.*
• InternalServerErrorResponse: Status code 500. Applicable to 10 of 15 methods.*
• NotFoundErrorResponse: Status code 404. Applicable to 9 of 15 methods.*
• BadRequestErrorResponse: Status code 400. Applicable to 5 of 15 methods.*
• ForbiddenErrorResponse: Status code 403. Applicable to 4 of 15 methods.*
• RequestTimeoutErrorResponse: Status code 408. Applicable to 4 of 15 methods.*
• TooManyRequestsErrorResponse: Status code 429. Applicable to 4 of 15 methods.*
• PaymentRequiredErrorResponse: Status code 402. Applicable to 3 of 15 methods.*
• PayloadTooLargeErrorResponse: Payload Too Large: File size exceeds 3MB limit. Status code 413. Applicable to 1 of 15 methods.*
• UnsupportedMediaTypeErrorResponse: Unsupported Media Type: Invalid audio file format. Status code 415. Applicable to 1 of 15 methods.*
• ResponseValidationError: Type mismatch between the data returned from the server and the structure expected by the SDK. See error.rawValue for the raw value and error.pretty() for a nicely formatted multi-line string.

* Check the method documentation to see if the error is applicable.

Additional Example Code

Additional example code can be found in the examples directory.