JUHE API Marketplace
Comprehensive Documentation

API Documentation

Everything you need to integrate and use our APIs effectively with guides, references, and examples

/
APIs
Back to Documentation

Text-to-Speech API

3 min read

This API provides a text-to-speech (TTS) service that converts written text into high-quality spoken audio. The service is powered by Microsoft Edge's TTS engine, allowing developers to easily integrate voice generation into their applications.

API Endpoints

1. Generate Speech

This is the core endpoint for converting a string of text into an audio file. It returns a temporary URL to download the generated MP3 file.

  • Functionality: Converts text to speech.
  • Method: POST
  • Endpoint: /tts/v1/generate

Query Parameters

ParameterRequiredTypeDescription & Example
apikeyYesstringYour unique API Key for authentication.
textYesstringThe text you want to convert to speech. Example: Hello, world!
langNostringThe language code for the voice. Defaults to en-US.
genderNostringThe preferred gender of the voice. Used to select a voice when voice is not specified. Example: female
voiceNostringThe specific voice name to use. This parameter has the highest priority. If provided, it overrides lang and gender. Example: en-US-JennyNeural

Available lang values:

  • en-US (American English)
  • zh-CN (Mandarin Chinese)
  • zh-TW (Taiwanese Mandarin)
  • ja-JP (Japanese)
  • ko-KR (Korean)
  • fr-FR (French)
  • de-DE (German)
  • it-IT (Italian)

Responses

Successful Response (Code 200)

A successful request returns a JSON object containing a direct download link for the audio file.

JSON

{ "code": "200", "msg": "Request processed successfully", "data": { "success": true, "url": "https://storage.juheapi.com/tts-audio-bucket/20250625/c4d5e6f7-a8b9-4c1d-8e7f-9a0b1c2d3e4f.mp3?Expires=1719369635&Signature=ABC...", "message": "Text to speech conversion was successful. The audio file is available for download.", "selected_voice": "en-US-Standard-F" } }

  • data.url: The temporary URL to download the generated MP3 audio file. Note that this link is time-sensitive.
  • data.selected_voice: The actual voice model that was used for the conversion.

Error Response

If the request fails, the API will return an error code and message.

JSON

{ "code": "string", "msg": "string" }

2. List Voices

This endpoint allows you to retrieve a list of all available voices supported by the service.

  • Functionality: Lists all available voices.
  • Method: GET
  • Endpoint: /tts/v1/list-voices

(Note: Use this endpoint to find the exact names for the voice parameter in the generation request.)

⚠️ Important Considerations

  1. API Key is Mandatory: Every request to the /generate endpoint must include a valid apikey.
  2. Voice Selection: For consistent results, it is highly recommended to use the /list-voices endpoint to find a specific voice name and use it in your requests. If you don't specify a voice, the system will select one based on the lang and gender parameters.
  3. URL Expiration: The audio url returned in a successful response is temporary and will expire. You should download the file to your own storage if you need to use it permanently. Do not use this URL for long-term embedding.