Cloud Text-to-Speech API with 8 Voices and 23 Languages

By LinguaSync editorial team · Updated 2026-11-18

Welcome to LinguaSync Team. This page details the technical specifications and operational facts of our cloud text-to-speech API, designed for developers integrating audio synthesis into HR and training platforms. You will find precise information on our 8 voice presets, 23 supported languages, and the specific request parameters required for the POST /v1/audio/speech endpoint.

We focus on delivering consistent, multilingual voiceovers without the overhead of studio recording. Here you can verify our pricing model, data privacy commitments, and technical limits such as the lack of streaming, SSML, or custom voice cloning support. Whether you are evaluating integration feasibility or reviewing account structures, this guide provides the concrete data needed to move forward.

Cloud Text-to-Speech API with 8 Voices and 23 Languages

Frequently asked questions

What is the LinguaSync API?

LinguaSync is a cloud text-to-speech API that converts text into audio files via a simple POST request. It supports the same request shape as the OpenAI speech endpoint, allowing you to send text and receive audio in formats like mp3, wav, opus, flac, or pcm. This makes it easy to integrate voice generation into your corporate training workflows.

Which voices are available?

We offer eight voice presets: aria, nova, luna, and sage (female); and felix, milo, atlas, and orion (male). Each voice has a distinct tone, from warm narrators to energetic promo styles. You can select any voice for any supported language, ensuring consistent audio quality across your multilingual learning materials.

How much does the API cost?

Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full. There are no monthly plans, seats, or minimum spends, allowing you to scale costs directly with your team’s audio generation needs without paying for unused capacity.

Is my data used for training?

No. Input text is used only to produce the audio and is not used for training. We respect your content’s privacy by ensuring your instructional materials remain yours. Only request metadata like time, characters, and status is kept for billing purposes, keeping your core data isolated from model improvement processes.

Do you store generated audio?

No. Generated audio is returned in the response and not stored on our servers. This ensures that your specific training content is not stored on our servers. This approach minimizes storage costs and reduces data retention risks, keeping your audio assets under your direct control.

How do I pay for the API?

Payments are made via USDT on the TRON network (TRC-20). The minimum top-up is $5, and credits are added automatically within minutes. We do not accept cards, PayPal, or subscriptions, and there are no invoices with VAT. Your balance does not expire, so you can top up as needed for your team’s usage.

Is there a free trial?

Yes. Signing in with Google provides $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. This allows you to test the API’s quality and integration speed before committing to a top-up for your larger corporate training projects.

Can I use the OpenAI SDK?

Yes. The API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.playck222.com/v1 and using your LinguaSync key. This allows you to leverage existing code and familiarity with OpenAI’s tools while benefiting from our pricing and voices.

What languages are supported?

We support 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If you do not set the language, it is guessed from the script, defaulting to English for Latin text.

Is there a rate limit?

Yes. Each API key is limited to 60 requests per minute. Before your first top-up, this limit is 10 requests per minute. Longer texts are split into parts of up to 4,096 characters. Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins.

Do you offer voice cloning?

No. We do not offer custom voice cloning, voice uploading, or voice design. Our eight presets are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. If you need a specific voice not in our list, you will need to use one of our existing presets.

Is there an SLA for uptime?

No. We do not offer an SLA, uptime guarantee, or enterprise contract. Our service is designed for flexibility rather than guaranteed availability. While we strive for reliability, there is no formal commitment to specific uptime percentages or compensation for downtime, making it ideal for non-critical or batch-processing training content generation.

How do I contact support?

Support is available by email only. We do not offer a phone number, live chat, or dedicated account managers. For questions about your API key, billing, or technical issues, please reach out via the contact page.

Are the voices based on real people?

Yes. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), which includes public-domain audiobook readings from LibriVox. These are not imitations of specific celebrities or politicians. Each voice is a preset with a distinct tone, designed for clear and engaging audio content.

API Overview

Sound wave illustration for: API Overview

LinguaSync provides a straightforward cloud API for text-to-speech generation. Teams send text input and receive synthesized audio files through a standard POST endpoint, designed to integrate seamlessly into existing HR and instructional design workflows without complex setup.

Send text, receive audio via POST endpoint

Send text, receive audio via POST endpoint

The core interaction uses a POST request to https://api.playck222.com/v1/audio/speech. You provide a JSON body containing the text (up to 4096 characters) and desired parameters, then receive the audio file directly in the response. This simple request-response cycle fits easily into automated content pipelines.

Compatible with OpenAI SDKs by changing base_url

Compatible with OpenAI SDKs by changing base_url

Because the request shape matches the OpenAI speech endpoint, you can use official OpenAI SDKs by simply updating the base_url to https://api.playck222.com/v1 and using your LinguaSync API key. This reduces integration time for developers already familiar with standard TTS patterns.

Supports MP3, WAV, Opus, FLAC, and PCM formats

Supports MP3, WAV, Opus, FLAC, and PCM formats

Select the response_format parameter to output audio as MP3, WAV, Opus, FLAC, or PCM. This flexibility allows you to choose the optimal balance between file size and quality for your specific training platforms or LMS integrations.

Voices and Languages

Sound wave illustration for: Voices and Languages

The API supports 23 languages, including English, Spanish, and Japanese. Any voice can speak any of these languages. If the language field is not set, the system guesses the language from the script, defaulting to English for Latin text. This ensures consistent delivery for multilingual corporate training materials without manual configuration for every voice.

8 presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion

8 presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion

Choose from eight distinct presets to match your instructional tone. Female voices include Aria (warm narrator), Nova (upbeat), Luna (storytelling), and Sage (calm instructor). Male options cover Felix (energetic promo), Milo (conversational), Atlas (neutral news), and Orion (deep documentary). These presets allow HR teams to maintain consistent voice quality across diverse learning modules.

  • 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

Support for 23 languages including English, Spanish, and Japanese

We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Voices are not language-specific; any preset can deliver any supported language. For non-English Latin-script text, explicitly set the language parameter to ensure accurate synthesis.

Voices based on licensed LibriTTS-R recordings

Our voices are derived from the LibriTTS-R dataset (CC BY 4.0), sourced from LibriVox public-domain audiobook readings. This foundation provides high-quality speech without the overhead of studio recording. Every generated audio file carries an inaudible watermark, clearly marking the content as synthetic speech for compliance and transparency.

Pricing and Payment

Sound wave illustration for: Pricing and Payment

We charge $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. Failed requests are free, ensuring you only pay for successful synthesis. There are no monthly plans, seats, or minimum spend requirements, making it easy to scale your HR training audio production up or down.

$10 per 1 million characters ($0.01 per 1,000 chars)

Our pricing is straightforward: $10 per million characters. This flat rate applies regardless of voice or format choice, though tts-1-hd uses the same engine and price. Since spaces and punctuation count as characters, a 4,000-character lesson costs just $0.04. You can generate content at scale without worrying about complex tiered structures or hidden fees.

  • No monthly plans or seats
  • Failed requests are free
  • Balance never expires

Free trial credit of $0.50 for Google sign-ups

Start testing immediately with a $0.50 credit when you sign up using Google. This provides approximately 50,000 characters of audio, valid for 7 days. If you prefer email and password registration, accounts begin without trial credit. This allows your team to evaluate quality before committing to larger volumes.

Top-up via USDT (TRC-20) on the TRON network

We accept USDT on the TRON network (TRC-20) for top-ups. The minimum deposit is $5, and credits appear automatically within minutes. We do not support credit cards, PayPal, or VAT invoices. This crypto-only approach keeps our overhead low, allowing us to maintain consistent pricing without subscription complexities.

  • Minimum top-up: $5
  • Automatic credit within minutes
  • No cards or PayPal

Data Privacy

Sound wave illustration for: Data Privacy

We prioritize your data integrity by ensuring that input text is processed solely for the purpose of audio synthesis. Your scripts are not used to train our models, meaning your proprietary training materials remain distinct from our engine’s development data.

Input text used only for synthesis, not for training

When you send text to our API, it is used exclusively to generate the requested audio file. We do not use this input to improve or train our underlying models, ensuring your corporate training content remains private and secure.

Generated audio returned in response and not stored

The resulting audio file is returned directly in the API response to your application. We do not persistently store the generated audio files, minimizing the risk of data leakage or unauthorized access to your finished voiceovers.

Request metadata kept only for billing purposes

We retain minimal request metadata, specifically the timestamp, character count, and status, solely for accurate billing and usage tracking. This data is not used for analytics or training purposes.

Data Privacy

Technical Limits

Sound wave illustration for: Technical Limits

Our API delivers complete audio files via standard HTTP responses, meaning there is no streaming, WebSocket, or SSML support. Each request returns a finished file, which fits batch processing workflows but does not allow real-time partial audio playback or fine-grained pronunciation control beyond the provided voice presets.

No streaming, WebSocket, or SSML support

We focus on reliable, completed audio generation. You send text and receive the full file; you do not get a live stream or structural markup tags for nuanced control.

No voice cloning or custom pronunciation lexicons

The system uses eight licensed presets based on LibriTTS-R recordings. We do not offer custom voice cloning, uploading your own voice, or phoneme dictionaries for specific word pronunciations.

Rate limit of 60 requests per minute per key

Each API key allows 60 requests per minute (10 per minute before the first top-up). Requests are processed sequentially, so high volume may queue slightly. Longer texts are split into 4096-character chunks to manage this efficiently.

Support and Contact

Sound wave illustration for: Support and Contact

Support is handled entirely through email, ensuring you have a written record of every interaction. We do not offer a phone number or live chat, so please allow a bit more time for our team to respond to your technical questions.

No SLA or uptime guarantee provided

We operate as an independent service without enterprise contracts or formal service-level agreements. While we strive for reliability, we do not guarantee specific uptime percentages or compensation for downtime, keeping our infrastructure simple and cost-effective for your team.

Accounts created per site with unique API keys

Each site in our network maintains its own independent accounts. Your API key is unique to this specific storefront, so ensure you are using the correct base URL and credentials when integrating with your HR or instructional design workflows.

You can issue a new key at any time via your dashboard, instantly invalidating the previous one for security.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. This preset is particularly effective for delivering consistent audio content across large teams and diverse departments.

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. openai-node on GitHub
  3. MDN: Web Speech API
  4. LibriTTS-R paper (arXiv 2305.18802)
  5. ISO 639 language codes
  6. W3C WAI: making audio and video accessible
  7. TRON developer hub: TRC-20
  8. Tether (USDT)
  9. Creative Commons Attribution 4.0
  10. LibriTTS-R corpus (OpenSLR 141)
  11. IETF RFC 7845: Ogg Opus
  12. LibriVox public-domain audiobooks

More on this site