Frequently asked questions
Who runs the WayAudio API?
An independent team of indie developers builds and maintains the WayAudio API. We are not affiliated with OpenAI, ElevenLabs, or any major tech brand. Our focus is on providing a straightforward, reliable text-to-speech endpoint for developers who need consistent synthetic speech without enterprise overhead or complex integrations.
Are the voices licensed correctly?
Yes. Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We ensure that every generated audio file is legally clear for your use, providing consistent, license-safe speech optimized for in-cabin listening and dashboard interfaces.
Do you store my input text?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata, such as time, characters, and status, strictly for billing purposes and account management.
How do I contact support?
Support is available by email only. There is no live chat or phone support. You can reach us via the contact page or by emailing the support address listed in our documentation. We aim to respond to inquiries as quickly as possible.
Is there a phone number for help?
No. We do not have a phone number for help. All support is handled via email. This keeps our operations lean and allows us to focus on maintaining the API infrastructure and delivering consistent performance for indie developers integrating synthetic voices into their navigation apps.
Do you have an office address?
No. We are a distributed team and do not maintain a physical office address for public visits. Our operations are entirely digital, managed through our API endpoints and support channels. This structure allows us to remain agile and focused on delivering reliable text-to-speech services.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API mimics the OpenAI speech endpoint structure for ease of use, but we are an independent storefront. Our voices and infrastructure are entirely our own.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons Attribution license. Our voices are based on recordings from LibriTTS-R, which uses this license. It allows you to use the content freely, even commercially, as long as you provide appropriate attribution. This ensures our synthetic speech is license-safe for your projects.
Do you use AI for voice generation?
We use synthetic voice technology based on licensed recordings. Our system generates speech from text using these presets. The voices are based on LibriTTS-R and LibriVox data, ensuring consistent, high-clarity audio for navigation apps.
Can I sue if the voice is bad?
We provide a standard API service. While we strive for high clarity, we do not offer an SLA or uptime guarantee. If a synthesis fails, you are not charged.
Do you hire voice actors?
No. We do not hire voice actors for new recordings. Our eight voice presets are derived from existing licensed recordings (LibriTTS-R and LibriVox). We do not upload new voices or offer custom voice cloning. The voices are fixed presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion.
Is the API open source?
No. The API itself is not open source. We use the OpenAI SDK structure for compatibility, but our implementation is proprietary. You can use the official OpenAI SDKs by changing the base_url, but the underlying engine and infrastructure are not publicly available or open source.
Where are your servers located?
Our infrastructure is cloud-based and distributed to ensure reliability. We do not offer on-premise installs or certifications like SOC 2 or HIPAA. The API is accessible globally via standard HTTP requests to our endpoints.
Do you have a privacy policy?
Yes. Input text is used only to produce audio and is not used for training. Generated audio is not stored. We retain request metadata for billing. For more details, refer to our privacy policy linked in the footer. We prioritize data minimization and clarity for our users.
Who we are
We are an independent team of developers building high-clarity synthetic voice solutions for car navigation and dashboard interfaces. We focus on practical, license-safe speech that integrates smoothly into in-cabin audio systems.
Indie developer team
Our team operates without corporate overhead, allowing us to prioritize developer needs and straightforward integration over complex business structures. We write code that works with standard HTTP requests and OpenAI-compatible SDKs.
Focus on automotive audio
We designed our API specifically for indie car developers who need consistent, clear audio for navigation prompts. Our voices are optimized for in-cabin listening, ensuring intelligibility even in noisy driving environments.
No corporate backing
We are not affiliated with OpenAI, ElevenLabs, or any major tech giant. We operate independently, meaning our pricing and features are driven by developer feedback rather than corporate strategy.
Voice licensing and sources
Our voices are built from licensed recordings of the LibriTTS-R dataset and public-domain audiobook readings from LibriVox. This foundation provides a diverse range of vocal styles, from warm narrators to energetic promotional tones, optimized for in-cabin listening without the need for expensive studio sessions.
LibriTTS-R license (CC BY 4.0)
The core voice models derive from LibriTTS-R, which operates under the Creative Commons Attribution 4.0 International license.
LibriVox public domain
Additional voice characteristics are sourced from LibriVox, a collection of public-domain audiobook recordings. These recordings are free from copyright restrictions, allowing us to offer a broader set of vocal presets without licensing fees that could drive up your per-character costs.
Clear attribution requirements
While the API handles the heavy lifting of synthesis, you must ensure proper attribution if required by your specific use case under CC BY 4.0. We recommend checking the license details for your integration, as our API does not automatically append metadata to audio files.
- Voice data is not used for further training
Data policy and privacy
We process your input text solely to generate the requested audio file. Your source text is not used to train our models or improve the voice engine, ensuring your content remains distinct from our training data.
Once the audio file is returned in the response, we do not store the generated audio itself. This minimizes data retention and keeps your specific voice outputs private and ephemeral.
Text not used for training
Input text is used exclusively to produce the audio and is never used for training.
Audio not stored after response
Generated audio is returned in the response and not stored.
Metadata kept for billing
Request metadata, including time, character count, and status, is retained solely for billing purposes.
Technical limitations
WayAudio delivers reliable, batch-oriented speech synthesis optimized for navigation systems and dashboard interfaces. Our architecture prioritizes consistent audio quality and predictable latency over real-time interactivity, ensuring that generated clips play smoothly within in-car audio environments without complex buffering logic.
While we support high-fidelity output formats like WAV and FLAC, our system does not provide progressive audio chunks. Developers should plan their UI accordingly, expecting full audio files after synthesis completes rather than incremental streaming data.
No streaming or WebSocket
We do not offer WebSocket connections or server-sent events for real-time audio streaming. Each POST /v1/audio/speech request returns a complete audio file once synthesis finishes.
No custom voice cloning
We do not provide custom voice cloning or allow you to upload your own voice samples. Our eight presets (e.g., Aria, Felix, Atlas) are fixed. If you need a specific brand voice, you must select from our available library.
No SSML support
Our API does not parse SSML (Speech Synthesis Markup Language). You cannot use tags for pauses, emphasis, or pronunciation rules. Control is limited to the speed parameter (0.25–4.0) and voice selection. This reduces payload size and complexity, making it easier to integrate into lightweight in-car infotainment systems that may not have an SSML parser.

Support and contact
We handle all technical questions, billing inquiries, and key issues via email. Our small, focused team manages every ticket personally to ensure accurate, context-aware responses without generic automated replies.
Email support only
Send your queries to [email protected]. Include your API key and a brief description of the issue, such as a failed request or integration question. We prioritize clarity and direct answers.
No live chat or phone
We do not offer live chat or phone support. This keeps our overhead low and allows us to focus on building a reliable API rather than maintaining large call centers. You will receive written responses that you can reference later.
Response time expectations
During high traffic or holidays, responses may take slightly longer. Since we are an indie team, we prioritize depth over speed, ensuring your technical question is fully resolved.
Mission and values
WayAudio is built by a small team of indie developers who understand the specific constraints of in-car audio interfaces. We prioritize clear, reliable speech synthesis that integrates seamlessly into navigation systems without the overhead of enterprise infrastructure.
Our mission is to provide high-clarity synthetic voices that are license-safe and optimized for in-cabin listening, ensuring that every character processed contributes to a natural driving experience.
Honest and specific claims
We avoid vague marketing language. Our claims are grounded in the actual performance of our TTS engine, such as the generation speed of roughly 25 characters per second and the specific voice presets available. We state exactly what the API does, including its limitations, so you know precisely what you are integrating.
- No invented statistics or client testimonials.
- All performance metrics are based on current API behavior.
No hype or superlatives
We do not claim to be the "best" or "fastest" TTS provider. We simply offer a consistent, predictable API for indie developers. Our voices are based on licensed recordings, and we provide clear attribution requirements rather than burying them in fine print. This transparency extends to our pricing and rate limits.
- No superlatives like "best" or "#1."
- No vague terms like "cutting-edge" or "revolutionary."
Developer-first approach
We design our API to be easy to integrate, with clear documentation and a straightforward pricing model. We focus on the technical needs of indie car developers, ensuring that the API is reliable and the support is direct. Our goal is to make it as simple as possible to add high-quality synthetic voices to your navigation app.
- Clear, step-by-step integration guides.
- Direct email support for technical questions.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. A neutral vocal quality reduces cognitive load by removing subjective emotional cues.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- IETF RFC 7845: Ogg Opus
- LibriTTS-R paper (arXiv 2305.18802)
- LibriVox public-domain audiobooks
- Python documentation
- Node.js documentation
- LibriTTS-R corpus (OpenSLR 141)
- ISO 639 language codes
- MDN: Web Speech API
- TRON developer hub: TRC-20
- W3C WAI: making audio and video accessible
- openai-node on GitHub
