Cloud Text-to-Speech API: Independent TTS Storefront

By NewsAudio Reader editorial team · Updated 2026-11-18

This page outlines the operational structure of NewsAudio Reader, an independent cloud text-to-speech API storefront designed for newsroom product teams. It details the product's focus on converting articles and transcripts into reliable audio assets for accessibility and multi-channel distribution, ensuring strict corporate standards for institutional users.

Here you will find specific information on voice licensing sources, data retention policies, and technical limitations. The page also clarifies our affiliation status, pricing model, and support channels, providing the exact facts needed to integrate this API into your existing editorial workflows without ambiguity regarding features or brand association.

Cloud Text-to-Speech API: Independent TTS Storefront

Frequently asked questions

Who runs the NewsAudio Reader site?

NewsAudio Reader is an independent storefront for the same text-to-speech API. Each site operates independently, meaning accounts and keys are specific to this domain. The product is a cloud API that converts text into audio files via a standard endpoint, designed for newsroom teams requiring reliable audio assets.

Are the voices based on real people?

Yes. The eight voice presets are based on licensed recordings from LibriTTS-R, which uses public-domain audiobook readings from LibriVox. These are recordings of human speech, ensuring a natural and consistent sound for your audio content.

Is the API affiliated with OpenAI?

No. NewsAudio Reader is not affiliated with OpenAI. We simply adopt the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base_url to https://api.playmomoo.com/v1, but we are an independent entity with separate pricing and infrastructure.

How is my input data used?

Input text is used exclusively to produce the requested audio file. We do not use your input text for training our models or improving the service. Once the audio is generated and returned in the response, the input text is not retained for any other purpose.

Is the audio output stored after generation?

No. Generated audio is returned directly in the API response and is not stored on our servers after delivery. We retain only request metadata, such as timestamp, character count, and status, strictly for billing and usage tracking purposes. Your audio assets remain under your control.

What license covers the voice recordings?

The underlying voice recordings are licensed under CC BY 4.0 from the LibriTTS-R dataset. This allows commercial use with attribution. As an independent storefront, we provide access to these voices via our API without additional licensing restrictions beyond the standard API usage terms and pricing.

How can I contact support?

Support is available via email only. We do not offer live chat, phone support, or dedicated account managers. For technical issues or billing inquiries, please send an email to our support address. Response times may vary depending on the volume of requests we are processing.

Do you offer custom voice cloning?

No. We do not offer custom voice cloning, voice design, or the ability to upload your own voice. You must choose from the eight available presets (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). Each voice is a fixed preset based on licensed recordings.

Is there a phone number for support?

No. We do not provide a phone number for customer support. All communication is conducted via email. This allows us to maintain a lean operational structure and keep costs low, passing those savings directly to you through our straightforward per-character pricing model.

Are the voices synthetic or recorded?

The voices are recorded. They originate from LibriVox public-domain audiobook readings licensed under CC BY 4.0. While the generation process is automated, the source material is human speech. Each generated file includes an inaudible watermark to clearly mark it as synthetic speech for transparency.

What is the CC BY 4.0 license?

CC BY 4.0 is a Creative Commons Attribution license. It allows you to share and adapt the material for any purpose, including commercially, provided you give appropriate credit. Our voice presets are derived from LibriTTS-R, which uses this license, ensuring legal clarity for your newsroom's audio assets.

Do you store personal data?

We retain request metadata, including time, character count, and status, primarily for billing purposes. Input text is used only for generation and not stored long-term. We do not collect extensive personal data beyond what is necessary for account creation and payment processing via USDT.

How do I verify the audio is synthetic?

Every audio file generated by our API contains an inaudible watermark that marks it as synthetic speech. This watermark is embedded during the synthesis process. It serves as a verification method to distinguish our AI-generated audio from human-recorded content for compliance and transparency purposes.

Is there an SLA for the API?

No. We do not offer a Service Level Agreement (SLA) or uptime guarantee. Requests are processed sequentially, and under load, they may wait in a queue. While we aim for reliability, there is no formal contract guaranteeing specific availability percentages or response times for your integration.

How much does the API cost?

The price is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spend requirements, allowing you to pay only for what you use.

Which payment methods are accepted?

We accept USDT on the TRON network (TRC-20) only. There are no credit cards, PayPal, or invoices with VAT. The minimum top-up is $5, and funds are credited automatically within minutes of transfer. Balances do not expire, and you can manage your account via the dashboard.

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 SDK by setting the base_url to https://api.playmomoo.com/v1 and providing your NewsAudio Reader key. This allows for easy integration into existing workflows that already utilize OpenAI-compatible clients.

Which 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 the language is not specified, it is guessed from the script.

What are the rate limits?

The limit is 60 requests per minute per key. Before the first top-up, the limit is 10 requests per minute. If you need to process longer texts, split them into parts of up to 4096 characters and join the resulting audio files. Requests are processed sequentially.

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 do not receive this trial credit. You can use this credit to test the API before making a USDT top-up for ongoing usage.

Editorial Team Overview

Sound wave illustration for: Editorial Team Overview

NewsAudio Reader operates as an independent storefront for a cloud text-to-speech API. We provide API keys and rate limits, providing a transparent environment for news distribution. Our infrastructure supports high-volume article conversion without enterprise contracts or SLAs.

The editorial team manages the product’s core functionality: converting text to audio files via a standard REST endpoint. We focus on reliability and compliance, ensuring generated assets meet accessibility standards for multi-channel distribution.

Independent storefront operation

NewsAudio Reader operates as an independent storefront for a cloud text-to-speech API. We provide API keys and rate limits, providing a transparent environment for news distribution. Our infrastructure supports high-volume article conversion without enterprise contracts or SLAs.

Editorial team structure

The editorial team manages the product’s core functionality: converting text to audio files via a standard REST endpoint. We focus on reliability and compliance, ensuring generated assets meet accessibility standards for multi-channel distribution.

Product focus areas

We prioritize newsroom workflows. Our API accepts standard text inputs and returns audio files in formats like mp3, wav, opus, flac, and pcm. Teams can integrate this directly into content management systems for rapid asset generation.

  • REST API integration
  • Accessibility compliance
  • Multi-channel distribution
  • Standard audio formats

Voice Licensing Details

Sound wave illustration for: Voice Licensing Details

The audio voices powering NewsAudio Reader are derived from the LibriTTS-R dataset, which consists of public domain audiobook recordings sourced from LibriVox. These recordings are the source for our eight voice presets, ensuring a natural and consistent synthetic output suitable for newsroom distribution.

LibriTTS-R source

Our TTS engine utilizes audio samples from the LibriTTS-R dataset. This corpus provides the raw vocal characteristics that define our eight presets, ranging from Aria’s warm narration to Orion’s deep documentary style, without relying on proprietary third-party voice licenses.

CC BY 4.0 license

The underlying recordings are available under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This allows us to incorporate these voices into our commercial API service.

Public domain recordings

Many of the source voices originate from LibriVox, where readers have donated their performances of public domain texts. Because the source material is in the public domain or openly licensed, we avoid the complex rights management associated with celebrity or proprietary voice cloning.

Voice Licensing Details

Data Usage Policy

Sound wave illustration for: Data Usage Policy

The API processes input text exclusively to generate the requested audio file. We do not retain your source text for training or model improvement, ensuring that your editorial content remains private during synthesis.

Input text usage scope

Your text is transmitted to the engine solely for the purpose of producing the audio asset. Once the file is generated and returned, the input data is not stored for secondary purposes.

Audio output retention

Generated audio files are returned directly in the response and are not stored on our servers. You retain full control over the resulting audio assets immediately after generation.

Billing metadata storage

We retain request metadata, including timestamp, character count, and status, exclusively for billing and usage tracking. This data ensures accurate charge calculation based on your consumption.

Product Limitations

Sound wave illustration for: Product Limitations

The API processes requests sequentially, meaning generation occurs in discrete blocks rather than as a continuous stream. This architecture ensures stable processing but requires clients to handle chunking for texts exceeding 4,096 characters. Users receive the complete audio file only after synthesis finishes, which may introduce latency for longer documents compared to real-time streaming solutions.

No streaming support

Requests are processed one after another, so under load a request may wait in a queue. Typical speed is roughly real time on long texts, but short phrases take a few seconds. Clients must wait for the full audio file to be returned in the response; partial audio chunks are not available during generation.

No SSML capability

The endpoint accepts plain text input without support for Speech Synthesis Markup Language. Users cannot control prosody, pause duration, or pronunciation via XML tags. Emphasis and intonation are determined automatically by the model based on the voice preset selected. For precise control, text must be pre-formatted by the client before sending.

No custom voice cloning

The service uses eight fixed presets derived from licensed LibriTTS-R recordings. Customers cannot upload audio samples to clone specific voices. Each preset has a distinct tone, ranging from warm narrators to deep documentary styles, but none can be modified or personalized with external audio data. All generated files carry an inaudible synthetic watermark.

Contact and Support

Sound wave illustration for: Contact and Support

NewsAudio Reader maintains a streamlined support structure designed for efficiency. All inquiries are handled exclusively via email, ensuring that product teams receive documented responses without the delays of phone queues or the unpredictability of live chat availability. This approach ensures written records of technical details are maintained.

Email support only

Our support team manages all technical and billing questions through a single email channel. This ensures that every request is tracked, responded to with precision, and archived for future reference. There is no tiered support system.

No phone number

We do not maintain a public phone line. This eliminates the need for customers to wait on hold during business hours and allows support agents to focus on resolving complex API integration issues without interruption. For newsrooms operating across multiple time zones, asynchronous email communication provides the necessary flexibility.

No live chat

Live chat widgets are not offered on the platform. This decision reduces infrastructure overhead and ensures that support staff are fully available to address detailed technical queries rather than managing multiple concurrent short conversations. All support interactions are thorough and documented, supporting audit requirements common in newsroom environments.

Contact and Support

Affiliation Statement

Sound wave illustration for: Affiliation Statement

NewsAudio Reader operates as an independent storefront for a cloud text-to-speech API. The product is not owned, endorsed, or affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in technical comparisons.

While the API endpoint structure mirrors the OpenAI speech endpoint, this is a compatibility feature, not an indication of corporate relationship. We are a distinct entity providing a standalone TTS service.

Not affiliated with OpenAI

We are not OpenAI. Our infrastructure, billing, and voice engine are entirely separate from OpenAI’s operations. The similarity in endpoint paths (e.g., /v1/audio/speech) is a design choice for developer convenience, allowing existing OpenAI SDKs to work with our service by simply changing the base URL.

Independent API provider

NewsAudio Reader is an independent API provider. We manage our own voice presets, language support, and pricing structure ($10 per million characters). Our development roadmap and technical decisions are made independently, without dependency on larger platform updates from major tech corporations.

No brand confusion

Brand names of other companies are used only in comparative contexts to describe technical compatibility or market positioning. We do not claim to be a subsidiary, partner, or reseller of any major tech brand. Our key, billing, and support are distinct from those of other TTS providers.

Pricing and Payment

Sound wave illustration for: Pricing and Payment

Pricing is calculated at $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation are counted as characters. Failed requests incur no charge, with the full amount returned to your balance. This straightforward model ensures you pay only for successful synthesis.

$10 per million characters

The rate is fixed at $10 per million characters, or $0.01 per 1,000 characters. Every character, including spaces and punctuation, counts toward this total. If a synthesis request fails, the charge is returned in full, ensuring you are not billed for unused audio.

  • $0.01 per 1,000 characters
  • Spaces and punctuation count as characters
  • Failed requests are free

USDT (TRC-20) top-ups

Top-ups are processed exclusively via USDT on the TRON network (TRC-20). The minimum deposit amount is $5. Credits are added automatically within minutes of a confirmed transfer. We do not accept credit cards, PayPal, or offer subscription-based billing cycles.

  • USDT on TRON (TRC-20) only
  • Minimum top-up: $5
  • No cards or PayPal

No monthly plans

There are no monthly plans, seats, or minimum spending requirements. Your balance does not expire. This pay-as-you-go structure allows newsroom product teams to scale audio production costs directly proportional to their content output without recurring commitments.

Pricing and Payment

Technical Specifications

Sound wave illustration for: Technical Specifications

The API endpoint mirrors the OpenAI speech schema, allowing direct integration with official OpenAI SDKs by adjusting the base URL to https://api.playmomoo.com/v1. Authentication uses a standard Bearer token, ensuring seamless adoption for existing infrastructure.

OpenAI SDK compatibility

Developers can utilize the official OpenAI libraries without custom wrappers. The request structure for text input, voice selection, and output format matches the standard specification exactly.

8 voice presets

The platform provides eight distinct voice profiles, categorized by gender and tone. Options include female voices like Aria and Nova, and male voices such as Felix and Atlas.

  • 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

23 supported languages

Any voice can speak any of the supported languages. The system guesses the language from the script if unspecified, defaulting to English for Latin characters.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. News outlets will amplify your launch, turning product updates into public conversation for your entire audience.

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. FFmpeg documentation
  3. IETF RFC 7845: Ogg Opus
  4. TRON developer hub: TRC-20
  5. ISO 639 language codes
  6. LibriTTS-R corpus (OpenSLR 141)
  7. LibriVox public-domain audiobooks
  8. Creative Commons Attribution 4.0
  9. openai-node on GitHub
  10. Tether (USDT)
  11. Node.js documentation
  12. LibriTTS-R paper (arXiv 2305.18802)

More on this site