Quickstart Guide: Generate Audio with the TTS API

By Voxyto editorial team · Updated 2026-11-19

This guide helps animation startups generate consistent, copyright-safe character voices using a simple API. You will learn how to send text and receive audio files that fit directly into your production pipeline. The endpoint follows the OpenAI format, so you can reuse existing integrations by just changing the base URL.

We cover authentication, request parameters, and voice selection with concrete examples. You will see how to handle rate limits, choose between tts-1 models, and manage your API key. This documentation is designed for developers who need reliable synthetic speech without legal headaches, focusing on clear workflows and exact specifications.

Quickstart Guide: Generate Audio with the TTS API

Frequently asked questions

How do I authenticate with the API?

Include your unique API key in the request header as Authorization: Bearer tts-.... You receive one active key per account, which you can view on the dashboard. This key authorizes all your text-to-speech requests.

What is the API endpoint?

Send a POST request to https://api.27bb.info/v1/audio/speech. The JSON body must contain the model, input text, voice selection, and desired response format. This endpoint handles all audio synthesis tasks.

Does it work with the OpenAI SDK?

Yes. The request shape matches the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.27bb.info/v1 and providing your site-specific key. This allows seamless integration with existing code.

What audio formats are supported?

You can choose between mp3, wav, opus, flac, or pcm formats. Select the response_format field in your request body. These options cover most standard audio needs for animation projects without requiring external conversion tools.

What is the character limit per request?

Each request supports up to 4096 characters of input text. For longer scripts, split your text into parts of this size and join the resulting audio files. This ensures consistent processing and manageable request sizes.

How do I set the language?

Pass an optional ISO language code in the request body. If omitted, the system guesses the language from the script, defaulting to English for Latin text. Explicitly setting it ensures correct pronunciation for non-English content.

What happens if a request fails?

If synthesis fails, you receive a full refund of the character charge. Failed requests are free, so you are not billed for errors. This protects your budget while you debug your integration or input data.

What are the rate limits?

You are limited to 60 requests per minute per key. Before your first top-up, this limit is 10 requests per minute. Requests are processed sequentially, so high load may cause queuing delays for your audio generation.

Can I use the same key for multiple projects?

Yes, each account has one active key that can be used across multiple projects or applications. You can issue a new key at any time, which immediately invalidates the old one, allowing you to rotate credentials easily.

How do I get a new API key?

Log in to your account dashboard and request a new key. The new key becomes active immediately, and the previous one stops working at once. This is useful for security rotations or separating different project environments.

What is the base URL?

The API base URL is https://api.27bb.info/v1. Use this prefix when configuring your SDK or HTTP client. All endpoints, including speech generation and voice listing, are relative to this base URL.

Is SSML supported?

No, the API does not support SSML. You must rely on the text input and voice selection for your audio output.

Is streaming supported?

No, the API does not support streaming or WebSocket connections. This is suitable for pre-rendered animation assets rather than live interaction.

Are there mobile SDKs?

No, there are no mobile SDKs. You can use the standard OpenAI SDKs or plain HTTP requests to integrate the API into your mobile applications. This gives you full control over the implementation.

First request

curl

curl https://api.27bb.info/v1/audio/speech \
  -H "Authorization: Bearer $TTS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
  --output hello.mp3

Python (openai)

from openai import OpenAI

client = OpenAI(base_url="https://api.27bb.info/v1", api_key="tts-...")

with client.audio.speech.with_streaming_response.create(
    model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
    response.stream_to_file("hello.mp3")

Node.js (openai)

import OpenAI from "openai";
import fs from "node:fs";

const client = new OpenAI({ baseURL: "https://api.27bb.info/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));
voice
ariafemale
novafemale
lunafemale
sagefemale
felixmale
milomale
atlasmale
orionmale
language
arالعربية
zh中文
daDansk
nlNederlands
enEnglish
fiSuomi
frFrançais
deDeutsch
elΕλληνικά
heעברית
hiहिन्दी
itItaliano
ja日本語
ko한국어
msBahasa Melayu
noNorsk
plPolski
ptPortuguês
ruРусский
esEspañol
swKiswahili
svSvenska
trTürkçe

Authentication

Sound wave illustration for: Authentication

Secure your character voices with a single active API key. This key authenticates all requests to the TTS endpoint, ensuring that your animation startup’s audio generation remains private and billed correctly to your account.

API Key Format

API Key Format

Your key is a string starting with tts- followed by alphanumeric characters. It is generated on the /get-api-key/ page after signing in with Google or email.

  • Format: tts-<random_string>
  • One active key per account

Authorization Header

Authorization Header

Include the key in every request using the standard HTTP Authorization header. This ensures the API recognizes your identity and applies your current balance limits.

  • Header: Authorization: Bearer tts-<your_key>

Key Management

You can issue a new key at any time via your dashboard. The old key stops working immediately, which is useful if you suspect exposure or rotate credentials between development and production environments.

Endpoint Overview

Sound wave illustration for: Endpoint Overview

The API provides three primary endpoints for interacting with the text-to-speech service. You will use the speech generation endpoint to convert text into audio, the voices endpoint to explore available options, and the models endpoint to check system status.

Speech Generation Endpoint

Send a POST request to https://api.27bb.info/v1/audio/speech with your text, voice, and format preferences. The endpoint returns the audio file directly, allowing you to integrate it into your animation pipeline instantly.

Voices Endpoint

Use GET https://api.27bb.info/v1/voices to retrieve the list of eight available voices, supported languages, and audio formats. This helps you select the perfect character tone before generating audio.

Models Endpoint

Access GET https://api.27bb.info/v1/models to verify the available models (tts-1 and tts-1-hd). Both use the same engine, so you can choose based on your quality needs without changing your integration logic.

Request Parameters

Sound wave illustration for: Request Parameters

Configure your API calls by selecting the model and preparing your input text. The API accepts standard TTS parameters to generate audio files from your animation scripts.

Ensure your text fits within the character limits and choose the appropriate voice and language to match your character's tone and origin.

Model Selection

Choose between "tts-1" for standard quality or "tts-1-hd" for higher fidelity. Both models use the same engine and pricing, so you can switch based on your project's needs without changing your integration logic.

Input Text Limits

Each request supports up to 4096 characters. Spaces and punctuation count toward this limit. For longer scripts, split your text into chunks and join the resulting audio files.

  • Maximum 4096 characters per request
  • Spaces and punctuation count as characters

Voice and Language Options

Select one of eight preset voices or let the system guess the language from the script. For non-English Latin text, explicitly set the language to avoid English defaults.

  • 8 voice presets available
  • 23 languages supported
  • Optional ISO language code

Response Formats

Sound wave illustration for: Response Formats

The API returns audio files in your chosen format, ensuring compatibility with your animation pipeline. You can select from mp3, wav, opus, flac, or pcm via the response_format parameter.

The response returns the audio file directly (binary or base64 depending on implementation), without a JSON body containing metadata.

Supported Audio Formats

You may request audio as mp3, wav, opus, flac, or pcm. MP3 and OPUS offer efficient compression for web delivery, while WAV and FLAC provide lossless quality for post-production. PCM is available for raw data processing.

  • mp3, wav, opus, flac, pcm

JSON Response Structure

The response returns the audio file directly; it does not contain a JSON object with status, character count, or a URL. This structure allows easy parsing in any programming language.

Audio File Delivery

Generated audio is returned directly in the response. For longer texts split into parts, you receive multiple audio segments that you can join. No files are stored on our servers after delivery.

Rate Limits and Queues

Sound wave illustration for: Rate Limits and Queues

Your API key allows 60 requests per minute once funded. This limit applies to the key, not the account, so ensure your integration respects these bounds to avoid throttling during high-volume animation asset generation.

60 Requests Per Minute

After your initial trial or first top-up, you can send up to 60 synthesis requests every minute. This throughput supports consistent character voice production for short clips without overwhelming the service.

Initial Limit for New Keys

New keys start with a lower limit of 10 requests per minute. This restriction applies until you complete your first top-up, ensuring fair usage before scaling up your animation pipeline.

Queue Processing Behavior

Requests are processed sequentially. Under load, your synthesis jobs may wait in a queue before generation begins. Expect longer wait times during peak usage, but all requests are processed in order.

  • Requests are processed one after another
  • Wait times increase under load
  • No priority queuing system
Rate Limits and Queues

Error Handling

Sound wave illustration for: Error Handling

API errors usually indicate invalid requests or temporary service limits. When synthesis fails, your account balance is automatically restored, ensuring you only pay for successful audio generations. This safety net allows you to experiment with different voices and formats without financial risk.

Common issues include exceeding character limits or using unsupported audio formats. If a request fails, check the response body for a specific error code. These codes help you quickly identify whether the problem is with your input data or a temporary network issue.

Common Error Codes

Errors typically fall into four categories: invalid authentication, invalid request body, rate limit exceeded, or internal server errors. Review the response status code to determine the cause. Most errors provide a clear message to help you correct your request parameters.

  • 401 Unauthorized: Check your API key format and ensure it starts with 'tts-'.
  • 400 Bad Request: Verify that 'model', 'input', and 'voice' are provided correctly.
  • 429 Too Many Requests: You have exceeded the 60 requests per minute limit.
  • 500 Internal Server Error: Try again later; the service is temporarily unavailable.

Failed Request Refunds

If synthesis fails, the charge is returned in full. This ensures that you are never charged for audio that was not successfully generated. The refund is immediate and automatic.

  • Failed requests are free.
  • Refunds are applied instantly to your account balance.

Troubleshooting Tips

Ensure your input text does not exceed 4096 characters. If it does, split the text into smaller parts and join the resulting audio files. Also, verify that the voice you selected supports the language you specified. If issues persist, contact support via email.

  • Check text length limits.
  • Verify voice and language compatibility.
  • Split long texts into chunks.

Code Examples

Sound wave illustration for: Code Examples

Generate audio instantly using standard HTTP requests or the OpenAI Python SDK. Both methods require your API key and follow the same JSON structure, making integration straightforward for animation pipelines.

Use the curl example for quick testing, or the Python snippet to automate voice generation within your production scripts. Both handle the necessary headers and payload formatting automatically.

Curl Command Example

Test the API directly from your terminal to verify voice quality and latency before integrating into your animation workflow.

Replace YOUR_API_KEY with your actual key from the dashboard.

  • `curl -X POST https://api.27bb.info/v1/audio/speech -H 'Authorization: Bearer YOUR_API_KEY' -H 'Content-Type: application/json' -d '{"model": "tts-1", "input": "Hello world", "voice": "nova", "response_format": "mp3"}' -o speech.mp3`

OpenAI SDK Usage

Leverage the official OpenAI SDK by pointing it to our base URL. This allows you to use familiar methods like client.audio.speech.create().

Ensure you set the base_url to https://api.27bb.info/v1 and provide your tts-... key.

  • import openai, client = openai.OpenAI(api_key='YOUR_API_KEY', base_url='https://api.27bb.info/v1'), `speech_file = client.audio.speech.create(model='tts-1', voice='nova', input='Welcome to our animated story.')`

Python Request Example

For custom workflows, use the requests library to send JSON payloads. This gives you full control over headers and error handling.

Parse the response bytes directly to save the audio file or feed it into your animation rendering engine.

  • `requests.post('https://api.27bb.info/v1/audio/speech', headers={'Authorization': 'Bearer YOUR_API_KEY'}, json={'model': 'tts-1-hd', 'voice': 'sage', 'input': 'Narrating the scene...', 'response_format': 'wav'})`

Voice Selection

Sound wave illustration for: Voice Selection

Voxyto offers eight distinct voice presets designed for animation and cartoon production. These voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. You can select any voice for any of the 23 supported languages, including English, Japanese, and Spanish.

List Available Voices

The API provides eight presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). Retrieve the full list via GET /v1/voices.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional
  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Voice Characteristics

Each voice is a preset based on licensed recordings from LibriTTS-R. They are not custom voice clones; they are preset voices based on licensed recordings. Every generated file includes an inaudible watermark marking it as synthetic speech.

Selecting the Right Voice

Match the voice to your character’s role. Use Atlas for neutral news-style narration or Orion for deep documentary tones. For energetic promo scenes, Felix works well. Remember, any voice can speak any of the 23 supported languages; set the language parameter for non-English Latin text to ensure accuracy.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. You receive the full voiceover asset to download and integrate into your animation software.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. TRON developer hub: TRC-20
  3. FFmpeg documentation
  4. openai-python on GitHub
  5. ISO 639 language codes
  6. IETF RFC 7845: Ogg Opus
  7. curl documentation
  8. Tether (USDT)
  9. Node.js documentation
  10. Creative Commons Attribution 4.0
  11. LibriVox public-domain audiobooks
  12. Python documentation

More on this site