Frequently asked questions
Who runs this site?
WordCaster is an independent storefront for the same text-to-speech API used across the network. We are not a large enterprise but a focused service designed for indie developers and no-code builders who need reliable cloud TTS without complex infrastructure.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our endpoint structure mimics OpenAI for convenience, but we operate independently with our own keys, billing, and infrastructure.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide the raw audio data that powers our synthetic speech engine for all generated files.
Is the audio licensed for commercial use?
The underlying recordings are from LibriVox public-domain readings and LibriTTS-R (CC BY 4.0). Generated audio files are returned in the response and not stored by us. We do not offer specific commercial license documents, but the source material permits broad usage.
What data do you store?
We keep request metadata including time, character count, and status for billing purposes. Input text is used only to produce the audio and is not stored long-term. Generated audio is returned in the response and not stored on our servers.
Do you use my text for training?
No. Input text is used exclusively to produce the audio for your request. It is not used for training our models or improving the service. Your data remains private to the generation process and billing records.
Is there a phone number for support?
No. We do not have a phone number. Support is provided via email only. This allows us to maintain a lean operation focused on delivering a reliable API without the overhead of traditional customer service channels.
Do you have a live chat?
No. We do not offer live chat support. All inquiries are handled through email. This approach ensures that support requests are documented and addressed thoroughly without the pressure of real-time conversation, fitting our independent storefront model.
What is your SLA?
We do not offer an SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. We aim for reliability but do not contractually guarantee specific availability percentages or response times.
Do you have a GDPR certificate?
No. We do not have a GDPR certificate or other certifications like SOC 2 or HIPAA. We are an independent service and do not maintain the extensive documentation required for such formal certifications, focusing instead on transparent data practices.
Can I request a custom voice?
No. We do not offer custom voice design or the ability to request specific new voices. You must choose from the eight available presets: aria, nova, luna, sage, felix, milo, atlas, or orion. Each has a distinct tonal quality.
Do you offer voice cloning?
No. We do not offer custom voice cloning for customers, nor do you upload your own voice. The voices are fixed presets based on licensed recordings. We do not provide the infrastructure to clone or design new voices on demand.
How do I contact support?
Support is available via email only. There is no phone number or live chat. You can reach us through the contact page or by emailing the support address provided in your account dashboard or documentation.
Is the editorial team technical?
Our editorial team is technical and familiar with API workflows. We write specifically for indie developers and no-code builders, ensuring our documentation and content reflect real-world usage of the API, including rate limits, character counts, and integration steps.
Who we are
WordCaster is an independent storefront for a single cloud text-to-speech API. We are an editorial team focused on clarity, not a large enterprise. Our goal is to provide indie developers and no-code builders with a straightforward, reliable API for converting text into audio files.
Editorial team
We are a small group of developers and writers who value transparent documentation. We built this storefront to offer a simple interface for the API, ensuring that technical details are accurate and easy to understand for projects of any scale.
Independent storefront
Unlike major cloud providers, we do not manage the underlying infrastructure or voice models. We provide the gateway, billing, and key management. This independence allows us to offer a straightforward pay-as-you-go model without complex tiers or minimum commitments.
No affiliation
WordCaster is not affiliated with OpenAI, ElevenLabs, Google, or Amazon. Our endpoints mimic the OpenAI format for convenience, but we are a separate entity. We use our own voice presets derived from licensed recordings, distinct from any other brand's offerings.
Voice licensing
WordCaster’s voices are built on licensed recordings from the LibriTTS-R dataset, providing a transparent foundation for synthetic speech. This approach ensures that the audio quality is grounded in real, human performances rather than purely algorithmic generation.
The dataset originates from LibriVox, offering high-quality public domain audiobook readings. This allows indie developers to use reliable, consistent voices without navigating complex licensing chains for individual narrators.
LibriTTS-R source
All eight voice presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are derived directly from the LibriTTS-R dataset. This source provides the raw audio data used to generate the voices for every audio file.
The dataset contains hours of read text, providing the basis for natural prosody and clear articulation across all 23 supported languages. Each voice retains the distinct tonal qualities of its source recordings.
- Derived from LibriTTS-R dataset
- Basis for all 8 voice presets
- Ensures natural prosody and clarity
CC BY 4.0 license
The LibriTTS-R dataset is released under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This legal framework allows for the use, modification, and distribution of the underlying voice data for commercial purposes, including our API service.
Attribution is required under the license terms, acknowledging the original readers and the LibriVox project. This license structure supports our pay-as-you-go model.
Public domain readings
The source material consists of public domain audiobook readings from LibriVox volunteers. These recordings are free from copyright restrictions on the underlying text, allowing us to process and synthesize them without ongoing royalty fees.
This public domain status ensures that the voices themselves are not encumbered by exclusive rights, providing a stable licensing environment for your applications. You can use the generated audio in your products without additional clearance.
Data policy
WordCaster processes your input text exclusively to generate the requested audio file. We do not use your source text to train our models or improve the TTS engine. Once the audio is synthesized and returned to you, the original text is not retained for any other purpose.
The generated audio files are returned in the response and are not permanently stored on our servers. This ensures your content remains yours without lingering copies in our infrastructure.
Input text usage
Your text is used solely for synthesis. We do not repurpose your input for model training or algorithmic improvement. This means your unique scripts and data remain private to your workflow.
Audio storage
Synthesized audio is delivered via the API response and is not stored in our long-term archives. You retain full ownership of the generated files without dependency on our storage.
Billing metadata
We retain minimal metadata strictly for billing accuracy. This includes the timestamp, character count, and request status to ensure you are charged correctly for every synthesis attempt.
Failed requests are identified immediately, and any associated charges are reversed. This data is kept only as long as necessary for accounting and dispute resolution.
- Timestamp
- Character count
- Request status
- Billing reference
Honest limits
WordCaster is built for simplicity, not enterprise-grade guarantees. We operate as an independent storefront without formal service level agreements or uptime promises. This keeps our infrastructure lean and our pricing transparent for indie developers and no-code builders who prioritize flexibility over rigid contracts.
Support is handled entirely via email. There is no phone number or live chat waiting room. Our team reviews tickets directly, ensuring you get specific responses.
No SLA
We do not offer a Service Level Agreement. There are no financial credits or penalties tied to specific uptime percentages. Requests are processed sequentially, so under load, a request may wait in a queue.
No uptime guarantee
While we aim for consistent availability, we do not guarantee a specific percentage of uptime. Requests are processed sequentially, so under heavy load, synthesis may queue. This is normal for our pay-as-you-go model and does not constitute a failure of service.
Email support only
All support is conducted via email. We do not maintain a phone line or live chat widget.
There is no phone number to call for urgent issues. If you need immediate assistance, send an email with your account details and issue description. Our team prioritizes direct communication to resolve technical queries efficiently.
- No phone number
- No live chat
- Email only

Contact
WordCaster operates as a lean, independent storefront built for developers who prefer direct communication. Our team handles your questions directly.
We keep our contact methods simple and transparent. There is no complex ticketing system with multiple tiers or automated routing.
Email support
All inquiries are handled via email. This is our primary and only channel for technical questions, billing disputes, or API usage details. You will receive responses from the actual team managing the WordCaster infrastructure.
No phone number
We do not offer a phone number. Email allows us to attach relevant context directly to your issue.
No live chat
Unlike many SaaS platforms, we do not use live chat widgets.
Technical details
WordCaster provides a straightforward REST API compatible with standard OpenAI SDKs. The primary endpoint is POST https://api.playtoto155.com/v1/audio/speech, which accepts JSON bodies and returns audio files. Additional endpoints include GET /v1/voices for listing available voices and GET /v1/models for model details. Requests require an Authorization: Bearer header with your unique API key.
API endpoints
The API follows a simple request shape. You send text up to 4096 characters via the POST endpoint. For longer texts, split the input and join the resulting audio files. The system supports tts-1 and tts-1-hd models, both using the same engine. Authentication is handled via a single active key per account, which can be rotated instantly.
- POST /v1/audio/speech: Main synthesis endpoint
- GET /v1/voices: List voices and languages
- GET /v1/models: Retrieve model information
Rate limits
Each API key is limited to 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. Requests are processed sequentially, so under heavy load, synthesis may queue. Failed requests do not consume credits or count against your usage.
- Standard limit: 60 requests/minute
- Initial limit: 10 requests/minute
- Sequential processing may cause slight delays
Audio formats
You can choose the output format by setting the response_format field. Supported formats include mp3, wav, opus, flac, and pcm. This flexibility allows easy integration into various applications, from web players to voice assistants. Each generated file also contains an inaudible watermark to identify it as synthetic speech.
- mp3
- wav
- opus
- flac
- pcm
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice is based on licensed recordings from LibriVox, ensuring clear, professional audio without licensing complexity.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Tether (USDT)
- FFmpeg documentation
- LibriTTS-R paper (arXiv 2305.18802)
- OpenAI API reference: create speech
- openai-node on GitHub
- W3C WAI: making audio and video accessible
- Creative Commons Attribution 4.0
- MDN: Web Speech API
- openai-python on GitHub
- LibriVox public-domain audiobooks
- curl documentation
