Lumivoice: Cloud TTS API for Indie Developers

By Playr77 editorial team · Updated 2026-11-18

This page provides a complete overview of the Lumivoice Text-to-Speech API, designed specifically for indie developers who require a reliable, scalable audio generation solution without complex infrastructure. You will find clear documentation on our REST endpoint, voice catalog, and integration workflow, ensuring straightforward implementation for your projects.

Explore our technical specifications, including rate limits, character constraints, and supported audio formats. We detail our transparent pricing model, starting with a free trial credit, and explain how our licensed voices deliver consistent quality. Use this guide to understand exactly what the API offers, from language support to data privacy, before generating your API key.

Lumivoice: Cloud TTS API for Indie Developers

Frequently asked questions

What does "realistic" mean for this AI voice generator?

The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Each generated audio file carries an inaudible watermark identifying it as synthetic speech. The output is standard text-to-speech audio without emotion tags, SSML, or custom pronunciation lexicons, designed for clear and consistent narration rather than human-like nuance.

Which languages are supported besides English?

We support 23 languages: Arabic, Chinese, Danish, Dutch, 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 the language is not specified, the system guesses it from the script, defaulting to English for Latin text.

Can I use the voices for commercial projects?

The voice data is based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. The API provides the audio generation service. You can use the generated audio in commercial projects, provided you comply with the underlying licenses of the source recordings. No additional voice cloning or custom design rights are granted beyond the generated audio file.

How much does it cost to generate audio?

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. Balance does not expire, and you only pay for the characters you successfully process.

What happens if a request fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. You can retry the request or split the text if the failure was due to input constraints, such as exceeding the 4096 character limit per request.

Do I need to install any SDKs?

No. You can use the official OpenAI SDKs by changing the base_url to https://api.playr77.com/v1. Alternatively, you can use plain HTTP requests. There is no official SDK specific to Lumivoice, no mobile SDK, and no WordPress plugin. The API endpoint follows the same request shape as the OpenAI speech endpoint.

Is there a limit on how long the text can be?

Each request supports up to 4096 characters. For longer texts, you must split the input into parts of this size and join the resulting audio files. Typical generation speed is roughly real time, so processing long texts may take time. Requests are processed sequentially, so under load, a request may wait in a queue.

Can I change my API key later?

Yes. You can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. There is only one active key per account. You can manage your keys directly on the /get-api-key/ page alongside your balance and usage statistics.

How do I pay for the service?

Payments are accepted via USDT on the TRON network (TRC-20) only. The minimum top-up amount is $5. Credits are added automatically within minutes after the transfer. We do not accept credit cards, PayPal, or subscriptions. There are no invoices with VAT. You can top up your balance as needed without any monthly commitment.

Is there a free trial available?

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. The trial allows you to test the API’s capabilities before committing to a USDT top-up. Unused trial credit expires after the 7-day period.

Do the voices sound different in different languages?

No. There are 8 voice presets (e.g., Aria, Nova, Felix) that can speak any of the 23 supported languages. The same voice model is used regardless of the language setting. If you do not specify a language, the system guesses it from the script, defaulting to English for Latin text.

Can I control the speed of the speech?

Yes. You can adjust the speed parameter between 0.25 and 4.0. This allows you to slow down or speed up the audio generation. The speed adjustment applies to the final audio output. You can set this parameter in your API request along with the model, voice, and input text.

What audio formats are supported?

We support mp3, wav, opus, flac, and pcm formats. You can specify the desired format in the response_format field of your API request. The audio is returned directly in the response. No streaming or WebSocket support is available for real-time partial audio delivery; you receive the complete file upon request completion.

How long are my request logs kept?

Request metadata, including time, characters, and status, is kept for billing purposes. Input text is used only to produce the audio and is not stored for training. Generated audio is returned in the response and is not stored by our servers. We do not retain long-term logs of the audio content itself.

First request

curl

curl https://api.playr77.com/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

How It Works

Sound wave illustration for: How It Works

Lumivoice provides a straightforward REST API for text-to-speech synthesis. Developers send a POST request to the endpoint and receive audio files in seconds. The workflow is designed for simplicity, allowing indie developers to integrate audio generation without managing complex infrastructure, though requests are processed sequentially and may wait in a queue under load.

The system processes requests sequentially, ensuring consistent output. Under normal load, generation speed is roughly real-time, with short phrases taking only a few seconds. Failed requests are processed without charge, ensuring transparent billing for every attempt.

Simple REST Endpoint

Simple REST Endpoint

Interact with Lumivoice via a standard HTTP POST request. The endpoint is located at https://api.playr77.com/v1/audio/speech. This structure mirrors the OpenAI speech endpoint, allowing you to use existing OpenAI SDKs by simply updating the base URL to https://api.playr77.com/v1.

  • Method: POST
  • Endpoint: /v1/audio/speech
  • Base URL: https://api.playr77.com/v1

JSON Request Body

Send your text and configuration parameters in a JSON body. The primary field is input, containing the text to convert (up to 4096 characters). You must specify the model (tts-1 or tts-1-hd), the voice preset, and the desired response_format. Optional parameters include speed (0.25–4.0) and a specific language ISO code.

Authentication is handled via a Bearer token in the Authorization header. Use your unique API key, which you generate after signing up. If the language is not specified, the system guesses it from the script, defaulting to English for Latin text.

Instant Audio Delivery

Upon successful processing, the API returns the audio file directly in the response. The response format depends on your request, supporting mp3, wav, opus, flac, or pcm. For longer texts exceeding 4096 characters, you must split the text into parts, send separate requests, and join the resulting audio files.

Requests are processed sequentially. During high load, a request may wait in a queue before synthesis begins. Typical processing speed is approximately 25 characters of text per second of generated audio. Failed requests do not incur charges.

Voice Catalog

Sound wave illustration for: Voice Catalog

The Lumivoice API provides eight distinct voice presets, engineered for consistent audio generation across diverse content types. Each voice is assigned a specific tonal character to match your application’s needs, from clear narration to energetic dialogue.

Female Voices: Aria, Nova, Luna, Sage

Aria delivers a warm, clear narration style. Nova offers a bright, upbeat tone. Luna provides a soft, storytelling voice. Sage ensures calm, instructional clarity.

Male Voices: Felix, Milo, Atlas, Orion

Felix brings energetic, promo-ready dynamics. Milo provides a friendly, conversational tone. Atlas maintains a neutral, news-like delivery. Orion offers a deep, documentary-style voice.

Licensed Recordings from LibriVox

All eight voices are based on licensed recordings from the LibriTTS-R dataset, sourced from LibriVox public-domain audiobook readings. This foundation ensures high-quality, natural-sounding synthesis while maintaining clear licensing origins for your generated audio files.

Supported Languages

Sound wave illustration for: Supported Languages

Lumivoice supports 23 languages, allowing voices to speak any supported language regardless of the voice preset. Language detection is automatic based on the script, though Latin-script text defaults to English if the language is not explicitly set.

European Languages: French, German, Spanish

European languages such as French, German, and Spanish are supported across all voice presets. Developers can specify the ISO language code to ensure correct pronunciation, preventing the system from defaulting to English for Latin-script text.

Asian Languages: Hindi, Japanese, Korean

Asian languages including Hindi, Japanese, and Korean are supported. Each voice preset can render these languages with consistent quality, enabling developers to localize content without managing multiple voice models.

Other Supported: Arabic, Russian, Turkish

Additional languages such as Arabic, Russian, and Turkish are available. The API handles the specific phonetic requirements of these languages within the standard request structure, ensuring accurate synthesis for diverse global audiences.

Integration for Developers

Sound wave illustration for: Integration for Developers

Lumivoice mirrors the standard OpenAI speech endpoint structure, allowing you to integrate our API using existing OpenAI SDKs with a simple base URL adjustment. Send a POST request to /v1/audio/speech with your JSON body, and receive an audio file directly in the response.

OpenAI SDK Compatibility

Use the official OpenAI SDKs by setting the base URL to https://api.playr77.com/v1. This ensures seamless compatibility with your current codebase, requiring minimal changes to switch providers. Authenticate using your Bearer token in the standard header format.

  • Standard JSON request body
  • Compatible with OpenAI SDKs
  • Simple base URL override

Multiple Audio Formats

Select the output format that best fits your application’s needs. Supported formats include mp3, wav, opus, flac, and pcm, giving you flexibility for web streaming, high-quality archival, or lightweight processing.

  • mp3, wav, opus, flac, pcm
  • No format conversion required
  • Direct audio file response

Speed Control

Adjust the speech rate between 0.25 and 4.0 to match the pacing of your content. This feature allows precise control over audio length and tone, ensuring the voice aligns with your project’s rhythm.

  • Speed range: 0.25–4.0
  • Fine-tune pacing
  • Adjustable per request

Pricing Model

Sound wave illustration for: Pricing Model

Lumivoice charges $0.01 per 1,000 characters, with a standard rate of $10 per million characters. Spaces and punctuation count toward the total. Failed requests are refunded in full, ensuring you only pay for successful synthesis.

Pay Per Character

Billing is precise and transparent. Each character in your input text, including spaces, is tallied. The cost scales linearly with usage, making it easy to predict expenses for projects of any size.

No Monthly Fees

There are no subscriptions, seats, or minimum spend requirements. You pay only for what you use. Balances do not expire, and you can top up via USDT (TRC-20) whenever needed.

Free Trial Credit

Signing in with Google provides $0.50 in trial credit, valid for 7 days. This allows approximately 50,000 characters of generation. Accounts created with email and password do not receive this trial credit.

Pricing Model

Technical Specifications

Sound wave illustration for: Technical Specifications

Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins. Typical generation speed is roughly real-time, processing approximately 25 characters of text per second of audio output. Short phrases may take a few seconds to generate.

Rate Limits and Queues

Each API key allows 60 requests per minute. Before the first top-up, the limit is stricter at 10 requests per minute. Requests are processed one after another, meaning high concurrency may introduce latency as the system queues incoming synthesis tasks.

  • 60 requests per minute per key after top-up
  • 10 requests per minute for new accounts
  • Sequential processing may cause queuing delays under load

Character Limits per Request

A single API call accepts input text up to 4,096 characters. Spaces and punctuation count toward this limit. If your text exceeds this threshold, you must split it into multiple requests to ensure successful synthesis.

  • Maximum 4,096 characters per request
  • Spaces and punctuation count as characters
  • Exceeding the limit requires splitting the text

Input Text Handling

For longer texts, split the input into parts of up to 4,096 characters and join the resulting audio files. The language field is optional; if omitted, the system guesses the language based on the script, defaulting to English for Latin text.

  • Split long texts into 4,096-character chunks
  • Join generated audio files for final output
  • Optional language detection defaults to English for Latin script

Use Cases

Sound wave illustration for: Use Cases

Lumivoice enables indie developers to integrate consistent, scalable audio generation directly into applications without managing complex infrastructure. The API supports straightforward integration, allowing teams to generate audio files on demand using simple REST endpoints and JSON request bodies.

Indie Game Narration

Generate character dialogue and ambient narration for games efficiently. With 8 licensed voices and support for multiple languages, developers can localize content quickly. The API handles up to 4096 characters per request; you must split longer texts and join the resulting audio files.

  • Support for 23 languages including English, Japanese, and Spanish
  • Consistent voice quality across game chapters
  • Fast generation speeds suitable for dynamic content

E-learning Modules

Create clear, instructional audio for educational content. Voices like Sage offer a calm, instructional tone ideal for tutorials. The API’s reliability ensures that learning materials are generated consistently, supporting up to 60 requests per minute for bulk content creation.

  • Calm, instructional voices for educational content
  • Support for various audio formats like MP3 and WAV
  • Efficient processing for bulk content generation

Accessibility Features

Enhance accessibility by converting text to speech for users with visual impairments. The API provides a simple way to add audio versions of text content, ensuring compliance with accessibility standards. Input text is used only for generation and not for training.

  • Support for multiple audio formats
  • Easy integration for accessibility features
  • Transparent data usage with no text retention

Data and Privacy

Sound wave illustration for: Data and Privacy

Lumivoice processes your input text exclusively for the purpose of generating the requested audio file. We do not retain your source text for machine learning model training or to improve future voice models. Your raw input remains isolated to the immediate synthesis request, ensuring that your specific content stays proprietary to your application.

Text Not Used for Training

The text you send to the API is used solely to produce the audio output. We do not analyze or store this text for training our underlying models. This ensures that your unique narratives, code snippets, or customer data remain confidential and are not repurposed by us for algorithmic improvement.

  • Input text is discarded after synthesis
  • No secondary use for model training

No Persistent Audio Storage

Generated audio files are returned directly in the API response and are not stored on our servers after delivery. This means your final audio outputs are not kept in our long-term storage infrastructure. You maintain full control over where the audio files are saved, whether in your cloud bucket or local device.

Metadata for Billing

We retain minimal request metadata, including timestamp, character count, and status, strictly for billing accuracy and service monitoring. This data allows us to verify charges against your usage and ensure consistent service delivery. No personal content or audio data is included in this billing metadata.

Get Started

Sound wave illustration for: Get Started

Access your dashboard to manage keys, balance, and usage metrics. The interface displays your current API key, available credit, and a ready-to-use cURL example for immediate testing.

Sign Up with Google

Navigate to /get-api-key/ and authenticate using your Google account. This method instantly grants a $0.50 free trial credit, valid for 7 days, allowing you to generate approximately 50,000 characters without payment details.

Generate API Key

Your unique Bearer token is displayed immediately upon login. You may issue a new key at any time; the previous key becomes invalid instantly, ensuring strict security without manual deactivation steps.

First Curl Request

Use the provided cURL example to send your first synthesis request. Point your client to https://api.playr77.com/v1, set the Authorization header with your key, and submit your text payload to receive audio data.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence.

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

More on this site