Frequently asked questions
Who runs this API?
ScribbleVoice is an independent storefront focused on indie developers and WordPress bloggers. We provide a reliable text-to-speech API without complex infrastructure. Our goal is to help you turn content into audio files easily, ensuring transparent pricing and no hidden fees for your projects.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R, which is available under the CC BY 4.0 license. Additionally, the audio samples originate from LibriVox public-domain audiobook readings. This ensures high-quality, legally cleared synthetic voices for your text-to-speech generation needs.
Is my data used for training?
No. Your input text is used only to produce the specific audio file you request. It is not used for training our models. We retain request metadata like time and character count solely for billing purposes, ensuring your content remains private and unused for other purposes.
How do I contact support?
We offer support exclusively via email. There is no phone number or live chat available. Please reach out to our support team through the contact page if you have questions about your API key, billing, or technical issues with the speech endpoint.
Do you have an SLA?
We do not offer an SLA or uptime guarantee. Our API is designed for indie developers and bloggers who need reliable service without enterprise contracts. While we strive for stability, we do not provide formal service level agreements or on-premise installation options for this cloud API.
Can I clone my own voice?
No, we do not offer custom voice cloning. You cannot upload your own voice or design a new one. We provide eight preset voices based on licensed recordings. If you need a specific voice, you must choose from our existing library of male and female presets.
Are the voices licensed?
Yes, our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Every generated file also carries an inaudible watermark marking it as synthetic speech, ensuring clear attribution and compliance with the licensing terms of our source audio materials.
Do you store generated audio?
No, we do not store the generated audio files. The audio is returned directly in the API response for you to download or embed. We keep request metadata, such as time and status, only for billing purposes. Your generated content remains transient and under your control.
Is this affiliated with OpenAI?
No, we are not affiliated with OpenAI. We simply use the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDK by changing the base_url to our API domain. We are an independent provider, distinct from any major tech brand.
How do I report a bug?
You can report bugs via email support. Since we do not have live chat or phone support, email is our primary channel for technical issues. Please include details about the request, error code, and context so our team can investigate and resolve the issue efficiently.
Can I request a new voice?
We currently offer eight preset voices and do not have a formal request process for new ones. Voices are based on licensed recordings. If you need a different voice, you must choose from our existing library. We do not offer custom voice design or cloning options.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For other cases, we do not offer traditional refunds since there are no subscriptions. Your balance does not expire, so you can use your credit whenever you are ready to generate audio.
Is the API open source?
No, the API itself is not open source. We provide a cloud-based service where you send text and receive audio. You can use the OpenAI SDK or plain HTTP to interact with it. We do not provide an official SDK of our own, nor is the backend code public.
What is the editorial team's background?
ScribbleVoice is built by a team focused on indie developers and WordPress bloggers. We understand the need for reliable, simple infrastructure.
Who We Are
We are a small, independent team building a text-to-speech API that respects your time and budget. We focus on indie developers and WordPress bloggers who need reliable audio integration without complex infrastructure or hidden fees.
Our team works directly with the code, ensuring every request is processed correctly. We avoid corporate bloat to keep things simple and honest for developers who just want their content turned into audio files.
Independent editorial team
We are not a large corporation with layers of management. We are a small group of developers who understand the daily challenges of building websites and apps. We handle the API ourselves, so when you need help, you get real answers from people who know the product inside out.
Focus on indie developers
Our API is designed for indie developers who need straightforward integration. We support standard workflows, like using the OpenAI SDK with a simple base URL change. Whether you are building a blog or a web app, we provide the tools you need to embed audio or let users download files easily.
No corporate overhead
Without large corporate overhead, we keep our operations lean. This means you get transparent pricing. We do not have sales teams pushing unnecessary features. We focus on delivering a reliable API that works well with WordPress and other platforms you already use.
Our Mission
We built this API to let indie developers and WordPress bloggers add reliable text-to-speech without complex infrastructure. Our goal is to turn your content into audio files you can embed or download, using a straightforward interface that fits into your existing workflow.
Simplify TTS integration
Our endpoint follows the same request shape as the OpenAI speech endpoint, so you can use the official OpenAI SDKs by simply changing the base_url. This means you don’t need to learn a new protocol or manage custom infrastructure to start generating audio.
Transparent pricing
We charge $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, and there are no monthly plans, seats, or hidden fees. Your balance never expires.
High-quality voices
We provide eight distinct voice presets, ranging from warm narrators to energetic promos, all based on licensed recordings from LibriTTS-R. Each generated file includes an inaudible watermark to clearly mark it as synthetic speech, ensuring clarity and trust in your audio content.
Voice Licensing
ScribbleVoice’s eight voice presets are built on licensed recordings from the LibriTTS-R dataset, ensuring consistent, high-quality synthetic speech for your blog or app.
Based on LibriTTS-R recordings
Our voices, including Aria, Nova, and Atlas, are derived directly from the LibriTTS-R dataset. This provides a reliable foundation for natural-sounding output without the need for complex model training.
CC BY 4.0 licensed
The underlying recordings are licensed under Creative Commons Attribution 4.0 International. This allows us to legally synthesize these voices and offer them to indie developers without restrictive usage clauses.
From LibriVox public domain
These recordings originate from LibriVox, a platform dedicated to public domain audiobooks. By leveraging these existing public domain readings, we ensure that our TTS engine rests on a clear, transparent legal basis.
Data Privacy Policy
We treat your data with simple, straightforward rules. When you send text to our API, it is used strictly to generate the audio response for that specific request. We do not use your input text to train or improve our models, ensuring your content remains yours.
Input text not used for training
Your input text is processed solely to produce the audio file you receive. It is not stored long-term for model improvement or used to train future versions of the engine. This means your unique content, whether blog posts or documentation, stays private and is not repurposed by us.
Generated audio not stored
Once the audio file is returned in the response, we do not keep a copy of the generated speech. This ensures that your spoken content is transient and not archived in our systems after delivery. You have full control over where that audio file is saved or embedded.
Metadata kept for billing only
We retain basic request metadata—such as timestamp, character count, and status—exclusively to calculate your usage and process billing accurately. This data is minimal and directly tied to your account’s financial records, not used for analytics or profiling.

Contact Us
We believe in clear, direct communication without the friction of call centers. Our team is small, technical, and focused on solving integration issues for indie developers and WordPress bloggers. When you reach out, you get a person who understands the API, not a script.
Email support only
Send your questions or bug reports to [email protected]. We monitor our inbox and aim to respond within 24 hours on weekdays. Please include your API key and the request ID from your response headers if you are reporting a specific issue.
- Support via email only
- Response within 24 hours on weekdays
- Include API key and request ID for faster debugging
No phone number
We do not maintain a phone line. Voice calls often interrupt deep work, and written communication allows us to reference exact error logs and JSON payloads more accurately. You can paste your error messages directly into the email, making it easier for us to replicate and fix the problem.
No live chat
There is no real-time widget on this site. Live chat can create false expectations of immediate answers and often lacks context. Our email support is asynchronous, allowing our engineers to take the time they need to provide a thorough solution without rushing to a ticket queue.
Our Limits
We operate without an SLA or uptime guarantee, meaning request processing may queue during high load. There are no enterprise contracts, so our support remains email-only with no phone or live chat options.
No SLA or uptime guarantee
Our infrastructure serves indie developers, but we do not promise specific uptime percentages or response time guarantees. Requests are processed sequentially, so longer texts may experience slight delays under load.
No enterprise contracts
We offer a straightforward, self-serve model with no custom enterprise agreements or dedicated account managers. Support is handled via email, and we do not provide phone numbers or live chat for technical queries.
No custom voice cloning
Our eight presets are based on licensed LibriTTS-R recordings and are not customizable. We do not offer voice cloning, emotion tags, or the ability to upload your own voice samples for synthesis.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Publish your latest coding discoveries and personal reflections using a reliable blogging platform to grow your independent audience effectively.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- ISO 639 language codes
- Python documentation
- openai-node on GitHub
- Node.js documentation
- W3C WAI: making audio and video accessible
- MDN: Web Speech API
- LibriTTS-R paper (arXiv 2305.18802)
- TRON developer hub: TRC-20
- LibriVox public-domain audiobooks
- OpenAI API reference: create speech
- curl documentation
