Frequently asked questions
Who runs NewsAudio API?
NewsAudio API is an independent storefront operated by a single team. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft or any other brand. Our focus is providing a reliable cloud API for editorial teams, offering transparent billing and consistent voice output without enterprise contracts or complex seat management.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Each generated audio file includes an inaudible watermark to mark it as synthetic speech, ensuring clear attribution and transparency regarding the source of the synthetic voice data.
Do you store my input text?
Input text is used only to produce the audio and is not stored or used for training. We retain request metadata, such as time, character count, and status, strictly for billing purposes. The generated audio is returned in the response and is not stored on our servers.
How can I contact support?
Support is available via email only. We do not offer phone support, live chat, or on-premise installation options. For technical issues or billing questions, please reach out via email. We aim to respond to all inquiries promptly via email communication.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint structure mimics the OpenAI speech endpoint for ease of use, allowing you to use official OpenAI SDKs by simply changing the base URL. We are an independent provider of text-to-speech services with our own pricing and infrastructure.
Do you have an SLA?
We do not offer an SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time for long texts. We provide a reliable service but do not contractually guarantee specific availability percentages or response times.
Is my data used for training?
No, your input text is used exclusively to generate the audio file and is not used for training our models. We retain request metadata for billing purposes only. The generated audio is returned in the response and is not stored, ensuring your content remains private and unused for other purposes.
Can I get a refund?
Failed requests are free, with the charge returned in full if synthesis fails. We do not offer refunds for successful requests or general credits. Balances do not expire. Top-ups via USDT on the TRON network are credited automatically within minutes. No invoices with VAT are issued.
Who We Are
NewsAudio API is built by an editorial team that understands the pressure of daily news cycles. We designed this API to handle the specific workflow of converting scripts and articles into broadcast-ready audio, ensuring consistent voice and fast turnaround for large teams.
We operate as an independent storefront, meaning we focus solely on delivering reliable text-to-speech services without the overhead of a larger corporate ecosystem. This structure keeps our billing transparent and our integration simple for editorial workflows.
Editorial team focused on news
Our background in newsrooms informs every technical decision. We prioritize practical, step-by-step integration that fits seamlessly into existing publishing pipelines, ensuring that editorial teams can scale audio production without enterprise-level complexity or opaque contracts.
Independent storefront
As an independent storefront, we maintain direct control over our API infrastructure and pricing model. This allows us to offer straightforward rates and a simple sign-up process, catering specifically to the needs of news publications without unnecessary features.
No corporate backing
We are not affiliated with OpenAI, Google, Amazon, Microsoft, or any other brand. Our independence means we are accountable directly to our users, offering clear support via email and avoiding the potential pitfalls of relying on third-party platform changes.
This independence also ensures that our service remains focused on the specific needs of news media, rather than being diluted by broader consumer or enterprise demands.
Voice Licensing
NewsAudio API’s voice models are built on high-quality source material. We use the LibriTTS-R dataset, which is licensed under CC BY 4.0, ensuring clear, professional audio suitable for editorial use.
LibriTTS-R (CC BY 4.0)
The core of our synthesis engine comes from LibriTTS-R. This dataset provides consistent, high-fidelity speech samples that allow our API to generate natural-sounding audio for news scripts and articles.
LibriVox public-domain readings
Many of our voice presets are based on public-domain audiobook readings from LibriVox. These recordings offer a wide range of tones, from calm narrators to energetic presenters, giving editorial teams distinct options.
Licensed recordings used
We rely on these licensed and public-domain recordings rather than proprietary voice designs. This approach keeps our infrastructure simple and our pricing transparent, as we do not carry the overhead of exclusive voice rights.

Data Privacy Policy
We respect the confidentiality of your editorial content. Input text is processed solely to generate the requested audio file and is never used to train our models or improve the underlying TTS engine.
Input text not used for training
Your scripts and articles remain private to your workflow. We do not retain your input data for machine learning purposes, ensuring your unpublished stories stay yours.
Audio not stored after delivery
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Once you have the file, we do not keep a copy for long-term archival.
Metadata kept for billing
We retain minimal request metadata, including timestamp, character count, and status, strictly for billing accuracy. This data helps us verify charges and resolve any discrepancies in your usage account.
Honest Limitations
NewsAudio API is designed for efficient batch processing of scripts and articles. We prioritize reliable, complete audio file generation over real-time interaction, ensuring your editorial workflow remains predictable and straightforward without the complexity of managing partial streams or complex markup tags.
No streaming endpoint
The API returns a complete audio file upon request completion. We do not offer a WebSocket or streaming endpoint for real-time partial audio. This design simplifies integration for editorial teams who need to deliver finished segments rather than managing live audio streams.
No SSML support
We do not support Speech Synthesis Markup Language (SSML). If you need precise control over pauses or emphasis, you must insert those cues directly into the input text using standard punctuation or explicit instructions. This keeps the API lightweight and easy to implement.
No voice cloning
We do not offer custom voice cloning or uploading of your own voice recordings. The eight preset voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain readings. This ensures consistent, broadcast-ready quality without the variability of individual voice samples.

Contact and Support
We keep support simple and direct. If you have questions about your API key, billing, or integration, our team is ready to help via email.
Email support only
All inquiries are handled through our support email address. We avoid complex ticketing systems to ensure your message reaches the right person quickly.
- Direct email access
No phone number
We do not maintain a phone line. This allows us to keep overhead low and pass those savings on to you through transparent pricing without enterprise contracts.
Response within business hours
You will receive a reply from a real person who understands news workflows.

Our Mission
NewsAudio API exists to bridge the gap between editorial scripts and broadcast-ready audio. We built this service for newsrooms that need consistent voice quality and fast turnaround without the overhead of enterprise contracts. Our goal is to provide a reliable, straightforward tool that integrates into existing publishing workflows.
Make TTS accessible for news
We focus on delivering clear, natural-sounding speech for articles, press releases, and scripts. By leveraging licensed public-domain recordings, we offer high-quality voices that sound professional yet authentic. This ensures your content remains engaging whether read by a human or generated by our API.
Transparent pricing
Pricing is simple: $10 per 1 million characters. There are no hidden fees, subscriptions, or minimum spends. You only pay for what you use, and failed requests are refunded instantly. This model allows editorial teams of any size to scale their audio production without budget surprises.
Simple integration
Our API follows standard conventions, making it easy for developers to implement. With just a few lines of code, you can send text and receive audio files in formats like MP3 or WAV. Support is available via email, ensuring you have assistance when you need it.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The news publication team collaborates across large divisions to ensure accurate and timely reporting.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- LibriTTS-R corpus (OpenSLR 141)
- openai-python on GitHub
- OpenAI API reference: create speech
- W3C WAI: making audio and video accessible
- openai-node on GitHub
- Creative Commons Attribution 4.0
- Tether (USDT)
- LibriVox public-domain audiobooks
- ISO 639 language codes
- IETF RFC 7845: Ogg Opus
- curl documentation
