Frequently asked questions
Are you affiliated with OpenAI?
No. PressSynth is an independent storefront for its own text-to-speech API. While the request format matches the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by simply changing the base URL to https://api.98wi.info/v1, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.
Who owns the voices used in the API?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Each generated audio file carries an inaudible watermark marking it as synthetic speech. The voices are presets like Aria, Nova, and Felix, derived from these licensed sources rather than custom recordings by our team.
Can I use the audio for commercial news?
Yes. The API generates audio files that you receive directly in the response. Input text is used only to produce the audio and is not used for training. Generated audio is not stored by us, allowing you to integrate the resulting MP3, WAV, Opus, FLAC, or PCM files into your commercial news broadcasts or newsletters.
Do you store the audio I generate?
No. Generated audio is returned in the response and not stored by PressSynth. We retain request metadata, such as time, character count, and status, strictly for billing purposes. Your input text is used only to produce the audio and is not used for training or other purposes beyond the immediate synthesis.
How do I contact support?
Support is available by email only. We do not offer a phone number, live chat, or on-premise support channels. For technical issues or billing questions regarding your API key or usage, please send an email to our support address. Response times are not guaranteed.
Is there an SLA for uptime?
No. PressSynth does not offer an SLA, uptime guarantee, or enterprise contract. Requests are processed one after another, so under load a request may wait in a queue. Typical speed is roughly real time, but short phrases may take a few seconds. We do not guarantee specific availability windows or performance metrics.
Do you offer enterprise contracts?
No. There are no enterprise contracts, monthly plans, seats, or minimum spends. You pay only for what you use at $10 per 1 million characters. Accounts are created per site with a single active API key. We do not provide dedicated infrastructure, custom SLAs, or negotiated volume discounts for large publishers.
Can I request a new voice?
No. We do not offer custom voice cloning, voice design, or the ability to upload your own voice. The API provides eight fixed presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. You can adjust speed and language, but the underlying voice models remain the eight licensed recordings from LibriVox.
Where are your servers located?
We do not offer data-center choice. We do not offer data-center choice or on-premise installation options. As an independent storefront, we do not provide details on specific regions where your data is processed or stored beyond the standard request metadata kept for billing purposes.
Do you have a privacy policy?
We state that input text is used only to produce audio and is not used for training, and generated audio is not stored. Request metadata is kept for billing. For specific data handling details, please contact us via email.
Are you HIPAA compliant?
No. PressSynth does not offer certifications such as HIPAA, SOC 2, or GDPR certificates. We are an independent API provider without enterprise contracts or specialized compliance guarantees. We do not offer certifications such as HIPAA, SOC 2, or GDPR certificates.
Do you offer a mobile SDK?
No. We do not offer an official SDK of our own, nor a mobile SDK, WordPress plugin, or browser extension. You can use the official OpenAI SDKs by changing the base URL to https://api.98wi.info/v1, or use plain HTTP requests. The API is designed for server-side integration rather than direct mobile client usage.
Can I get a refund if I overcharge?
Failed requests are free, with the charge returned in full if synthesis fails. For overcharges or billing issues, support is available by email. We do not offer automatic refunds for successful requests beyond the failed request policy. Balance does not expire, and top-ups via USDT are credited automatically within minutes.
Who is the editorial team?
PressSynth is described as an independent storefront for publishers. We do not provide biographies or names of staff members. For general inquiries, you can contact us via email.
Who we are
PressSynth is an independent cloud text-to-speech API designed for publishers who need reliable audio generation for digital news and newsletters. We provide a Python-friendly API to convert articles and scripts into broadcast-quality audio without requiring enterprise contracts or minimum spend.
Our infrastructure operates independently, ensuring that your text is used only for generation and not for training other models. We focus on delivering consistent, scalable audio output for editorial workflows, letting you manage your own keys and billing without vendor lock-in.
Independent API provider
We operate as a standalone service, distinct from major tech platforms. Our API follows the standard OpenAI request shape, allowing you to use existing OpenAI SDKs by simply changing the base URL to https://api.98wi.info/v1. This compatibility means your existing Python scripts can integrate with our voice engine with minimal code changes, while we handle the underlying synthesis.
No affiliation with major tech brands
PressSynth is not affiliated with OpenAI, Google, Amazon, or Microsoft. While our endpoint structure mirrors OpenAI's for ease of use, we are a separate entity with our own pricing, voices, and infrastructure. We do not use OpenAI's engines, nor are we endorsed by them. Our brand identity is built on transparency and direct publisher relationships.
Editorial team background
We understand the specific needs of newsrooms: the demand for clear, neutral narration for breaking news, and the need for reliable speed when processing long articles. We built this API to solve the gap between expensive enterprise TTS solutions and basic consumer-grade converters.
Voice licensing
PressSynth’s voice engine is built on licensed recordings from the LibriTTS-R dataset. These voices originate from LibriVox, a platform of public-domain audiobook readings. This foundation ensures that the audio you generate is legally sound and ready for commercial use.
LibriTTS-R license
The core voice models are derived from the LibriTTS-R dataset, which provides a consistent and high-quality base for our synthesis engine. This dataset provides a consistent and high-quality base for our synthesis engine.
CC BY 4.0 terms
All underlying voice recordings are licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). This means you can use the generated audio commercially, provided you attribute the original source if required by your specific distribution channel. The license is permissive, allowing integration into newsletters and digital news without restrictive royalties.
LibriVox public domain source
The original recordings come from LibriVox, a volunteer project providing public-domain audiobooks. Because these source recordings are in the public domain, they do not carry additional copyright encumbrances. This simplifies your rights management, as you are not licensing from a single proprietary voice actor but from a broad public-domain corpus.
Data policy
PressSynth processes input text solely to generate the requested audio file. We do not use your article content, newsletters, or scripts to train our models or improve the underlying engine.
Input text not used for training
Your source text is used exclusively for the immediate synthesis task. It is not stored long-term for model development, ensuring that your editorial content remains private and distinct from our training data.
No audio storage after generation
The generated audio files are returned directly in the API response. We do not store the resulting audio files after delivery, ensuring that your published audio assets remain under your control.
Billing metadata retention
We retain request metadata including timestamp, character count, and status for accurate billing and usage tracking. This minimal data ensures you are charged correctly without retaining the actual content or audio files.
Technical limitations
PressSynth provides a reliable, straightforward API for generating audio from text. We prioritize stable, predictable delivery of audio files over complex, real-time streaming infrastructures or intricate markup languages.
Our design keeps the integration simple for publishers, focusing on bulk generation and clear, consistent output without the overhead of advanced, often unnecessary, features.
No streaming support
The API returns complete audio files rather than streaming partial audio. Each request processes text up to 4096 characters and delivers the final file once synthesis is complete. This approach ensures consistent file integrity and simplifies integration for newsletters and on-demand articles.
No SSML or phoneme dictionaries
We do not support SSML, phoneme dictionaries, or custom pronunciation lexicons. Voices follow natural intonation patterns based on the input text. For specific pronunciation needs, adjust the input text directly rather than relying on markup tags.
No custom voice cloning
We offer eight fixed voice presets rather than custom voice cloning. You cannot upload a sample to create a unique voice model. All generated files carry an inaudible watermark marking them as synthetic speech, ensuring clear identification of AI-generated content.

Contact information
PressSynth operates as a lean, independent API provider, which means we prioritize asynchronous communication that allows our team to thoroughly address technical questions without the pressure of immediate response times. This approach ensures that every inquiry receives a detailed, accurate answer tailored to your specific integration needs.
We do not maintain a call center or real-time chat infrastructure, keeping our operational costs low and passing those savings directly to you. If you need assistance, you can reach us at [email protected] for reliable, documented support that fits into your workflow.
Email support only
Our primary and only support channel is email. When you submit a request, our engineering team reviews the details and responds with precise solutions. This method is ideal for sharing error logs, code snippets, and API configuration details without the friction of scheduling calls.
No phone number
We do not offer a direct phone line for customer inquiries. This decision aligns with our focus on asynchronous, documented communication. By avoiding voice support, we ensure that your support history is searchable and that you have a written record of the solutions provided.
No live chat
There is no live chat widget on our site. We found that instant messaging often leads to fragmented conversations that are difficult to trace later. Email provides a stable, persistent record of your support tickets, ensuring that complex technical issues are resolved efficiently without losing context.
Brand independence
PressSynth operates as an independent entity, distinct from the major technology platforms often associated with similar speech technologies. Our infrastructure and API endpoints are managed separately, ensuring that our service remains a neutral, scalable tool for publishers without reliance on proprietary ecosystems.
We do not claim endorsement or affiliation with any of the large cloud providers or AI labs. This independence allows us to offer a straightforward API that works alongside existing workflows, without being tied to the specific constraints or branding of a single tech giant.
Not affiliated with OpenAI
Although our API endpoint structure and request body shape mimic the OpenAI speech endpoint for ease of use, we are not owned by or part of OpenAI. The similarity is purely structural, designed to allow developers to switch providers by changing a single base_url configuration in their code.
- We do not use OpenAI's proprietary models or voice engines.
- Our API key format and rate limits are specific to PressSynth.
- We are not listed as a partner or subsidiary of OpenAI.
Not affiliated with Google
Our sign-in system supports Google accounts for convenience, but this is a standard authentication method, not an indication of ownership or integration with Google Cloud services. PressSynth is a separate company with its own billing, data policies, and infrastructure, independent of Google's ecosystem.
- We do not use Google Cloud TTS as our backend engine.
- Our billing is handled via USDT (TRC-20), not Google Pay or billing accounts.
- We are not a Google Cloud partner or reseller.
Not affiliated with Amazon
PressSynth is not connected to Amazon Web Services (AWS) Polly or Amazon.com. While we can be deployed on various cloud infrastructures, our brand, voice models, and API logic are entirely our own. We do not share resources or branding with Amazon's media or cloud divisions.
- We do not use Amazon Polly voices or engine.
- Our API is independent of Amazon Lex or Translate services.
- We are not an Amazon Alexa or Echo device partner.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. The service provides eight preset voices based on licensed recordings from LibriTTS-R and LibriVox.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- W3C WAI: making audio and video accessible
- OpenAI API reference: create speech
- LibriVox public-domain audiobooks
- LibriTTS-R corpus (OpenSLR 141)
- curl documentation
- Python documentation
- Node.js documentation
- LibriTTS-R paper (arXiv 2305.18802)
- IETF RFC 7845: Ogg Opus
- TRON developer hub: TRC-20
- MDN: Web Speech API
