Frequently asked questions
Who owns this website?
This website is an independent storefront for the VoxRoute text-to-speech API. It operates separately from major tech brands and is owned by the entity managing the 99dtpix.com domain. We are not affiliated with OpenAI, ElevenLabs, or any other voice synthesis provider mentioned in comparisons.
Are these voices generated by AI?
The voices are synthesized using a cloud API that processes text into audio files. Each generated file contains an inaudible watermark marking it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings, processed through our specific engine.
How are the voices licensed?
Our voices are based on the LibriTTS-R dataset, which is licensed under CC BY 4.0. They originate from LibriVox public-domain audiobook readings. This licensing ensures that the base voice data is cleared for commercial use, allowing you to generate audio without additional voice-specific royalty concerns.
Is my input text used for training?
No. Your input text is used solely to produce the requested audio file. We do not use your submitted text for model training or to improve our voice synthesis algorithms. The text is processed and returned as audio without being retained for future training datasets.
Do you store the generated audio?
No. The generated audio is returned directly in the API response and is not stored on our servers. We retain request metadata, such as time, character count, and status, strictly for billing purposes. Your actual audio output is not kept after delivery to your application.
Do you have an SLA?
We do not offer a Service Level Agreement (SLA). There is no guaranteed uptime percentage or specific latency targets. Requests are processed sequentially, so under load, a request may wait in a queue. We provide reliable service but do not contractually guarantee specific availability metrics.
Is there a phone number for support?
No, we do not have a phone number. Support is available via email only. There is no live chat or direct phone line for technical or billing inquiries. You can reach our support team through the contact page or by emailing the address provided in our documentation.
Do you offer enterprise contracts?
No, we do not offer enterprise contracts. We operate on a pay-as-you-go model with no monthly plans, seats, or minimum spend requirements. There are no custom enterprise agreements, dedicated support tiers, or volume discounts beyond the standard pricing. You pay only for the characters you generate.
Can I clone my own voice?
No, we do not offer custom voice cloning. You cannot upload your own voice recording to create a unique voice model. We provide eight preset voices (e.g., Aria, Felix, Atlas) based on licensed recordings. If you need a specific voice, you must choose from our available presets.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint structure mimics OpenAI’s speech endpoint for convenience, allowing you to use OpenAI SDKs by changing the base URL. However, we are an independent provider. Our voices, pricing, and infrastructure are entirely separate from OpenAI’s services.
How do I contact support?
You can contact support via email only. Visit our /contact/ page to find the support address. There is no phone number or live chat available. Please include your API key and account details in your email to help us resolve your issue efficiently.
What is the editorial team's background?
The editorial team focuses on providing honest, specific facts about the VoxRoute API for indie developers. We avoid hype and superlatives, focusing on concrete details like character counts, pricing, and technical constraints. Our content is written to help developers integrate our TTS API into transport and logistics systems.
Do you have a privacy policy?
Yes, we process data according to standard privacy principles. Input text is not used for training, and generated audio is not stored. Request metadata is kept for billing.
Are there any certifications like SOC 2?
No, we do not hold certifications like SOC 2, HIPAA, or GDPR certificates. We do not offer on-premise installations or data-center choices that would require such audits. We are an independent cloud API without the enterprise-level compliance documentation that larger providers typically maintain for regulated industries.
Who Runs This Site
VoxRoute is an independent storefront for the VoxRoute text-to-speech API, designed for indie developers building in-vehicle announcements and logistics dashboards. We operate without venture backing or corporate overhead, focusing solely on delivering reliable, license-cleared speech synthesis via a simple API that integrates directly with existing transport software stacks.
This site is one of several independent storefronts for the same underlying API. Each storefront operates independently, meaning accounts and keys are specific to this domain. We do not share user data or billing structures with other storefronts in the network, ensuring transparent and isolated management for your transport integration projects.
Editorial Team Background
We understand the constraints of in-vehicle displays and the need for deterministic audio generation in logistics dashboards.
We prioritize technical precision over marketing hype.
- Independent developers with transport software experience
- Daily API testing with real-world text inputs
- Technical precision over marketing hype
- Focus on deterministic audio generation
Independent Storefront Model
As an independent storefront, we offer direct access to the API without middlemen or reseller markups. Your API key and billing are managed entirely through this site. If you need to switch storefronts, you can issue a new key at any time, and the old one stops immediately, giving you full control over your access.
This model ensures that your account details, such as balance, trial credit, and usage statistics, are visible and manageable directly on this domain. There are no complex enterprise contracts or multi-layer billing structures to navigate, just straightforward access to the API for your projects.
No Affiliation with Major Brands
VoxRoute is not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We use the OpenAI SDK format for convenience, but our API is distinct and operates independently. Our voices are based on licensed recordings from LibriTTS-R, not from any major tech company's proprietary models.
We do not use the voices of celebrities or politicians, and we do not offer custom voice cloning. Our 8 voice presets are based on public-domain readings from LibriVox, licensed under CC BY 4.0. This ensures that your generated audio is clear, consistent, and free from unexpected licensing issues when deploying in commercial transport systems.
Voice Licensing
Our voice presets are derived from the LibriTTS-R dataset, which captures high-quality speech suitable for synthetic voice models.
LibriTTS-R Source
The voices are based on licensed recordings from the LibriTTS-R dataset. This provides a robust base for generating natural-sounding speech in transport announcements and dashboard updates without relying on proprietary, locked-in voice engines.
CC BY 4.0 License
The dataset is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This allows us to process and adapt the audio for our API while maintaining legal clarity for commercial use. You do not need to worry about hidden royalty fees for the voice synthesis itself.
Public Domain Readings
Many source recordings originate from LibriVox public-domain audiobook readings. These contributions ensure that the base voice characteristics are free from restrictive copyright claims, making the API reliable for long-term logistics and transit software deployments.
- Source: LibriVox public-domain audiobooks
- License: CC BY 4.0
- Dataset: LibriTTS-R

Data Policy
We process your input text solely to generate the requested audio file. The text is not used for training our models or improving voice quality.
Generated audio is returned in the API response and is not stored on our servers after delivery. Your input data is transient.
Input Text Usage ['We use your input text exclusively to produce the audio response. It is not retained for model training or voice improvement.', 'The text is processed on-demand and discarded once the audio file is generated and sent to you.']
Audio Storage Policy ['Generated audio files are streamed directly in the API response and are not stored on our servers.', 'We do not keep copies of the audio files you generate, ensuring your content remains ephemeral.']
Billing Metadata Retention ['We retain request metadata, including timestamp, character count, and status, to accurately calculate your usage and billing.', 'This data is kept only for accounting purposes and is not linked to the content of your text or audio.']
API Limits and Facts
The API enforces a hard limit of 60 requests per minute per key. Before the first top-up, this rate is reduced to 10 requests per minute. Requests are processed sequentially, meaning high load may introduce queueing delays.
Each request accepts up to 4096 characters of input text. For longer announcements, split the text into chunks and join the resulting audio files. Typical synthesis speed is roughly real-time, processing approximately 25 characters per second.
60 Requests per Minute
Every API key is capped at 60 requests per minute. This limit applies to all endpoint calls and ensures fair usage across the network. If you exceed this threshold, requests will be rejected until the window resets.
- Standard limit: 60 requests/minute
- Pre-top-up limit: 10 requests/minute
- Sequential processing may add queue time under load
4096 Character Limit
The input field accepts a maximum of 4096 characters, including spaces and punctuation. To handle longer transit announcements or dashboard updates, split your text into multiple requests and concatenate the returned audio files.
Short phrases typically take a few seconds to generate, while longer texts process at roughly real-time speed (25 characters per second). This ensures predictable timing for in-vehicle displays and public address systems.
No Streaming Support
The API does not support streaming, WebSockets, or real-time partial audio delivery. You receive the complete audio file in the response body once synthesis is finished.
Because requests are processed one after another, heavy concurrent usage may cause delays. Plan your integration to handle these waits gracefully, especially during peak hours.

Contact and Support
VoxRoute is built by indie developers for indie developers. We handle everything from server maintenance to voice licensing, so you can focus on your transport software. This site is an independent storefront for the same TTS API, not a subsidiary of any major tech brand.
Our support structure is simple and direct. We prioritize clear communication over complex ticketing systems, ensuring you know exactly who is handling your account and billing questions.
Email Support Only
All inquiries are handled via email. This allows us to maintain a clear audit trail for billing disputes and technical issues.
For urgent API key issues, mention your key prefix in the subject line.
No Live Chat
We do not offer live chat widgets on this site. This keeps our overhead low and allows our team to focus on resolving your specific API integration issues rather than managing multiple simultaneous conversations.
If you need immediate assistance, email is the most reliable channel. We avoid the queueing delays common in live chat systems.
No Phone Number
There is no dedicated phone number for VoxRoute support. Our team works asynchronously, which fits the workflow of most indie developers and logistics dashboards.
This approach ensures that you are never put on hold.

Honest Limitations
VoxRoute operates as an independent storefront for indie developers, meaning we do not offer the formal enterprise structures or guaranteed uptime metrics found in larger cloud providers. Our infrastructure is designed for reliability, but we do not publish a Service Level Agreement (SLA) to back that promise with financial penalties.
We also do not maintain enterprise contracts with volume discounts or dedicated account managers. Support is provided via email only, with no live chat or phone lines, keeping our operational costs low and passing those savings directly to you.
No SLA or Uptime Guarantee
We do not guarantee 99.9% availability or offer credits for downtime. Requests are processed sequentially, so under heavy load, synthesis may queue behind other users. For critical transport systems requiring strict uptime contracts, you should factor in your own redundancy strategies.
- No financial penalty for downtime
- No guaranteed response time
No Enterprise Contracts
Pricing is flat-rate per character, with no volume tiers or negotiated contracts. Accounts are managed individually via the dashboard. If your logistics dashboard requires a dedicated instance or custom billing terms, you will need to handle that outside our standard API model.
No Custom Voice Cloning
We do not offer voice cloning or the ability to upload your own voice samples. You must choose from the eight provided presets (e.g., Atlas for news, Luna for storytelling). While our voices are based on licensed LibriTTS-R recordings, you cannot create a unique synthetic voice of a specific person.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Welcome to the developer hub, where your creative vision meets the stage.
23 languages
Any voice speaks any of these languages.
