Frequently asked questions
Is ClearCast affiliated with OpenAI?
No. ClearCast is an independent storefront for a text-to-speech API. While the request shape matches the OpenAI speech endpoint, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We operate independently.
Where do the voices come from?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We use eight presets like Aria, Nova, and Felix. Every generated file carries an inaudible watermark marking it as synthetic speech.
Do you store my input text?
No. Input text is used only to produce the audio and is not stored. Generated audio is returned in the response and not stored. Only request metadata (time, characters, status) is kept for billing purposes.
Is my data used for training?
No. Input text is used solely to generate the audio file and is not used for training. We do not use your data to improve our models or for any other training purposes beyond 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. You can reach us via the contact page or the email link provided in your account dashboard.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For successful requests, refunds are not explicitly detailed beyond the failed request policy. Balance does not expire, and you can issue a new API key anytime.
Is there an uptime guarantee?
No. We do not offer an SLA or an uptime guarantee. 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.
Are the voices realistic?
Voices are based on licensed recordings from LibriVox and LibriTTS-R. They are natural-sounding presets like Aria or Felix. Every file carries an inaudible watermark marking it as synthetic speech. They are not imitations of real celebrities or politicians.
Do you support SSML?
No. We do not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You send plain text via the API. For control, you can adjust the speed between 0.25 and 4.0, or split text into parts under 4096 characters.
Can I use the audio commercially?
Yes. The underlying voices come from CC BY 4.0 and public-domain sources. You can use the generated audio for station announcements, app notifications, and digital signage. We do not restrict commercial use of the output files.
Is the API secure?
We use standard Bearer token authentication. You have one active key per account, which can be replaced instantly. We do not offer specific certifications like SOC 2 or HIPAA, but input text is not stored after generation.
Do you have a mobile app?
No. We do not have a mobile app or a browser extension. You interact with us via the web API using standard HTTP requests or the official OpenAI SDKs by changing the base URL to our API endpoint.
Can I clone a voice?
No. We do not offer custom voice cloning, voice design, or the ability to upload your own voice. We provide eight fixed presets. Custom cloning explains consent and the law, but we simply do not offer that feature.
What is the data retention policy?
Input text is used only to produce audio and is not stored. Generated audio is returned in the response and not stored. We keep request metadata (time, characters, status) for billing purposes only.
Who We Are
ClearCast is an independent storefront for a single text-to-speech API. We focus on transport product teams who need crisp, natural-sounding audio for station announcements, app notifications, and digital signage. We operate as an independent storefront, ensuring reliable character-based billing without unnecessary complexity.
Independent storefront
We operate as a standalone entity, not a subsidiary of a larger tech giant. This structure keeps our pricing simple: $10 per million characters, with no hidden fees or enterprise contracts. You get direct access to the API endpoint without navigating through a massive corporate ecosystem.
- Single API endpoint for all transport audio needs
- Direct billing via USDT with no VAT invoices
- Transparent character counting including spaces and punctuation
Product team focused
We design for developers and product managers who integrate audio into transit apps. Our API matches the OpenAI speech endpoint shape, allowing you to use familiar SDKs by simply changing the base URL. We provide clear documentation and curl examples to get you from signup to first audio file quickly.
- Compatible with official OpenAI SDKs
- Support for 23 languages including English, Spanish, and Mandarin
- Fast generation speeds suitable for real-time notifications
No affiliation with major brands
ClearCast is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Our voices are based on licensed recordings from LibriVox and the LibriTTS-R dataset. We do not use the branding or infrastructure of these major platforms, ensuring your audio assets remain uniquely yours.
- Distinct voice models based on LibriVox recordings
- Independent infrastructure and billing systems
Voice Licensing
ClearCast’s voices are built on high-quality recordings from the LibriTTS-R dataset, providing a natural foundation for transport announcements and app notifications.
This data originates from LibriVox, featuring public domain audiobook readings.
LibriTTS-R source
Our eight voice presets—like Aria, Nova, and Atlas—are derived from licensed recordings within the LibriTTS-R dataset. This source provides the distinct tonal qualities that make our audio suitable for station announcements and digital signage.
CC BY 4.0 license
The underlying data is available under the Creative Commons Attribution 4.0 International license.
LibriVox public domain
The recordings come from LibriVox, featuring public domain audiobook readings. This ensures that the source material is free from copyright encumbrances, allowing us to focus on delivering consistent, crisp audio for your transport products.
Data Privacy Policy
ClearCast processes your input text solely to generate the requested audio file. The text is not retained after synthesis.
Text used only for audio
Your input text is used exclusively for the immediate production of the audio file.
No training on input
Unlike many AI services, ClearCast does not use your input text for training models.
Metadata kept for billing
We retain request metadata, including timestamp, character count, and status, strictly for billing and usage tracking. This minimal data ensures accurate invoicing without storing your actual spoken content.
Honest Limitations
ClearCast is designed for straightforward text-to-speech generation rather than real-time audio streaming. You send a request via our API and receive the complete audio file once synthesis is finished. This model works well for station announcements, app notifications, and digital signage where immediate millisecond-level latency isn't critical.
No streaming support
We do not offer WebSocket or chunked streaming endpoints. Audio is returned as a final file (mp3, wav, opus, flac, or pcm). For most transport use cases, this is sufficient.
No custom cloning
We do not offer voice cloning or uploading of custom voice recordings. Our eight voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. You select from these presets; you cannot train a new voice model.
No SLA guarantee
We operate as an independent storefront without an enterprise Service Level Agreement. We do not guarantee specific uptime percentages, latency bounds, or on-premise installation options. Our infrastructure handles requests sequentially, so under heavy load, synthesis may wait in a queue before processing.
- No 99.9% uptime SLA
- No dedicated enterprise support tier
- No on-premise deployment option

Contact and Support
We are a small, independent team building tools for transport product teams. Because we focus on engineering our API rather than managing a large support staff, our communication channels are intentionally simple and direct.
Email support only
Our primary and only support channel is email. You can reach our team at [email protected]. For urgent matters regarding your API key or service status, email remains the fastest way to connect with a human who understands our system.
- Address: [email protected]
- Response time: within 1 business day
- Preferred for: API questions, billing, general inquiries
No live chat
We do not offer a live chat widget on our site. We prefer asynchronous communication because it allows our engineers to review context, check logs, and provide accurate answers without the pressure of real-time typing.
No phone number
There is no phone number to call. We find that email provides a better paper trail for technical troubleshooting and billing adjustments. If you need to discuss a complex integration or a specific billing discrepancy, you can attach logs, screenshots, or curl examples directly to your email, which we can analyze more thoroughly than in a voice conversation.
Our Mission
We built ClearCast to solve a specific problem: transport teams need clear, natural-sounding audio for station announcements, app notifications, and digital signage without complex infrastructure. Our API delivers this directly, letting you generate crisp audio files via simple HTTP requests.
Clear transit audio
We prioritize intelligibility and tone for public address systems. With eight licensed voices ranging from calm instructions to energetic promos, you can match the exact mood of your transit network.
Simple pricing
Pricing is straightforward: $10 per 1 million characters, with failed requests refunded in full. There are no monthly plans, seats, or hidden fees. You only pay for what you generate, scaling effortlessly from a few daily announcements to thousands.
Developer friendly
Our API mirrors standard request shapes, so existing OpenAI SDKs work by adjusting the base URL. Generate audio with a single POST request, handling up to 4096 characters per call, and integrate seamlessly into your transport product workflows.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Aria delivers a soft, storytelling quality that works well for detailed route explanations or station history segments.
23 languages
Any voice speaks any of these languages.
