Frequently asked questions
Who runs VoxGrid?
VoxGrid is an independent provider of cloud text-to-speech APIs. We operate as a standalone storefront for our TTS engine, serving large SaaS teams with multilingual notification needs. We are not a subsidiary of a larger tech conglomerate and maintain full control over our infrastructure and billing processes.
Are you affiliated with OpenAI?
No, we are not affiliated with OpenAI. Our API endpoint mimics the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base URL. This compatibility is a convenience feature, but we are a distinct entity with our own keys, pricing, and infrastructure.
How are the voices licensed?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide the acoustic baseline for our eight voice presets, ensuring legal compliance while delivering synthetic speech outputs for your applications.
Is the data used for training?
Input text is used solely to produce the requested audio file and is not used for training our models. Generated audio is returned in the response and not stored permanently. We retain request metadata, such as time, character count, and status, strictly for billing and usage verification purposes.
Do you have an SLA?
We do not offer a Service Level Agreement (SLA). Our service is provided on a best-effort basis without guaranteed uptime or performance metrics. Requests are processed sequentially, so under load, synthesis may experience delays. We prioritize reliability for large SaaS teams but do not contractually guarantee specific availability levels.
How do I contact support?
Support is available exclusively via email. We do not maintain a phone line or live chat channel. For inquiries regarding your account, billing, or technical issues, please send an email to our support address. We aim to respond to all customer communications promptly during business hours.
Is there a phone number?
No, we do not have a phone number. All customer support and inquiries are handled through email communication. This approach allows us to maintain detailed records of your requests and ensures that your issues are addressed by the appropriate technical or billing specialists without hold times.
Do you offer live chat?
No, we do not offer live chat support. You can reach our team via email for any questions or assistance. This ensures that your support tickets are documented and tracked effectively, allowing for thorough resolution of technical or billing issues without the transient nature of chat sessions.
What is the data retention policy?
Input text is used only to generate the audio and is not retained for training. Generated audio is returned in the response and not stored. We keep request metadata, including timestamp, character count, and status, for billing purposes. This data is retained to verify charges and usage history.
Are the voices synthetic or recorded?
The voices are synthetic, generated by our TTS engine. However, they are based on licensed recordings from LibriTTS-R and LibriVox. Every generated audio file contains an inaudible watermark that marks it as synthetic speech, distinguishing it from direct human recordings while maintaining high naturalness and clarity.
Do you have certifications like SOC 2?
We do not currently hold certifications such as SOC 2 or HIPAA. We are an independent API provider focused on delivering reliable text-to-speech functionality.
Is there an uptime guarantee?
No, there is no uptime guarantee. Our service is provided on a best-effort basis. Requests are processed one after another, so under high load, you may experience queueing delays. We strive for consistent performance but do not contractually guarantee specific availability percentages or compensation for downtime.
Can I upload my own voice?
No, you cannot upload your own voice for use in our TTS engine. We offer eight preset voices with distinct characteristics. We do not provide custom voice cloning or voice design features. You must choose from our existing library of eight licensed synthetic voices for your applications.
Do you offer voice cloning?
We do not offer custom voice cloning for customers. You cannot upload a sample to create a unique voice model. Our service provides eight preset voices based on licensed recordings. If you need a specific voice, you must select from our available options: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, or Orion.
Is there a mobile SDK?
No, we do not offer a dedicated mobile SDK. You can use our API via standard HTTP requests or the official OpenAI SDKs by adjusting the base URL. This approach allows you to integrate our TTS service into any mobile application using your existing development tools and libraries.
Do you have a WordPress plugin?
No, we do not offer a WordPress plugin. Our service is a cloud API accessed via HTTP requests. You can integrate it into your WordPress site by writing custom code or using a plugin that supports generic API calls. We focus on providing the API infrastructure rather than specific CMS integrations.
Is there a browser extension?
No, we do not provide a browser extension. Our product is a backend API for generating audio from text. You can integrate our service into web applications using JavaScript or any other language that supports HTTP requests. We do not offer standalone extensions for end-user browsing experiences.
Do you offer speech-to-text?
No, we do not offer speech-to-text services. Our product is strictly a text-to-speech API. We convert text input into audio files. We do not provide transcription, translation, dubbing pipelines, or video editing tools. Our focus remains on delivering high-quality synthetic voice generation via our API.
Do you offer translation services?
No, we do not offer translation services. You must provide the text in the desired language, optionally specifying the ISO code. Our API generates audio from the text you provide. We handle 23 languages but do not translate content between languages; you must manage the text input yourself.
Is there a video editing tool?
No, we do not offer a video editing tool. Our service generates audio files (MP3, WAV, OPUS, FLAC, PCM) from text. You are responsible for integrating this audio into your video production workflow. We provide the voice component but do not handle video assembly, editing, or rendering.
Editorial Team
VoxGrid operates as an independent entity, distinct from the major technology providers whose SDKs we emulate. Our editorial and development teams focus exclusively on maintaining the reliability of the TTS API for large SaaS notification pipelines. We do not maintain ties to the parent companies of the voice datasets we utilize.
Our support structure is streamlined and dedicated. Our team handles all inquiries directly via email. There are no automated tiers or third-party handoffs. This ensures that your team receives consistent, human-reviewed responses regarding API usage, billing discrepancies, or voice configuration questions.
Independent Operation
VoxGrid functions as a standalone storefront for the underlying TTS engine. We manage the infrastructure, billing logic, and voice presets independently. Our operational decisions are driven by the specific needs of large teams managing multilingual user notifications, ensuring that our uptime and rate limits align with enterprise-scale notification bursts rather than consumer traffic patterns.
No Affiliation
We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. While our API endpoint structure mirrors the OpenAI speech endpoint for ease of integration, we are a separate company. Our voice presets are derived from the LibriTTS-R dataset and LibriVox public-domain readings, not from proprietary models owned by the brands often compared to us.
Dedicated Support
Support is provided via email only. We do not offer a phone number or live chat widget. Our support team is available to assist with API key issuance, billing questions related to TRC-20 top-ups, and technical clarification on voice parameters. All communications are logged and handled by the same core team that manages the API infrastructure.
Voice Licensing
VoxGrid’s synthetic voices are derived from the LibriTTS-R dataset, which consists of licensed recordings from LibriVox public-domain audiobook readings. This foundation ensures that our eight voice presets—ranging from Aria to Orion—are built on legally cleared, high-quality source material without the need for complex rights management for end-users.
LibriTTS-R Dataset
The underlying audio samples originate from the LibriTTS-R dataset, providing a robust baseline for our text-to-speech engine. Each voice preset, whether female or male, is trained on this specific collection, ensuring consistent acoustic properties across all 23 supported languages.
- Based on licensed recordings from LibriVox
- Provides the acoustic baseline for all 8 voice presets
- Ensures consistent quality across English, Chinese, Arabic, and 20 other languages
CC BY 4.0 License
The LibriTTS-R dataset is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This allows VoxGrid to process, modify, and generate derivative audio files from the source material for commercial API delivery. Users receive synthetic audio files that carry an inaudible watermark, distinguishing them as generated content while maintaining clear licensing origins.
- CC BY 4.0 license covers the source dataset
- Permits commercial use and derivative work
- Inaudible watermark marks synthetic output
Public Domain Source
The original recordings come from LibriVox, a community of volunteer readers who provide public-domain audiobooks. Because the source texts and recordings are in the public domain, there are no ongoing royalty obligations for specific book titles. This structure keeps billing transparent, based solely on character volume rather than content complexity or copyright tiers.
- Source material from LibriVox volunteer readers
- Public-domain status eliminates per-title royalties
- Supports transparent, character-based billing
Data Policy
VoxGrid processes your input text exclusively to generate the corresponding audio file. We do not retain or reuse your input text for model training or other purposes after synthesis completes. This ensures your content remains private and isolated from our training datasets.
Input Text Usage
Input text is used only to produce the audio and is not used for training. The system consumes your characters to generate the voice output and discards the source text immediately after the audio file is created.
Audio Retention
Generated audio is returned in the response and not stored. Once the audio file is delivered to your client or server, we do not keep a copy on our servers. This minimizes storage costs and ensures that your audio assets remain under your control.
Billing Metadata
Request metadata (time, characters, status) is kept for billing. We retain timestamps, character counts, and success/failure status to calculate your usage accurately. This data is used solely to verify charges against your TRC-20 balance or trial credit.
Contact Information
We handle all VoxGrid inquiries exclusively through email. Our support team monitors the inbox and responds to technical and billing questions as capacity allows, ensuring clear communication without the noise of live channels.
Email Support Only
Send your questions to the support address listed on our contact page. We prioritize clarity and accuracy in our written responses, allowing you to reference specific details about your API usage or account status.
No Phone Number
We do not maintain a dedicated phone line. This structure allows us to remain an independent operation with streamlined overhead, passing those savings directly to our character-based billing model rather than maintaining voice infrastructure.
No Live Chat
There is no real-time live chat widget on this site. For asynchronous support that fits into your workflow, email remains our primary and only channel for direct communication with the VoxGrid team.

Product Limits
VoxGrid operates without a formal Service Level Agreement (SLA) or a published uptime guarantee. Requests are processed sequentially; under load, a request may wait in a queue before synthesis begins.
We do not hold specific industry certifications such as SOC 2, HIPAA, or GDPR compliance certificates. While input text is used only for generation and not training, we do not provide a separate certificate to verify this status.
No SLA
We do not offer a formal Service Level Agreement (SLA). Requests are processed in the order received, meaning synthesis may wait in a queue during periods of high demand. Typical speed is roughly real time, but short phrases may take a few seconds to generate.
- No formal SLA document
- Sequential request processing
- Queue delays possible under load
No Uptime Guarantee
We do not guarantee a specific percentage of uptime. The API is designed for reliability, but maintenance or unforeseen issues may cause temporary unavailability without prior notice or service credits.
No Certifications
VoxGrid does not hold external certifications such as SOC 2, HIPAA, or GDPR compliance certificates. While data practices are transparent, we do not provide third-party audited reports to verify these specific standards.
Network Structure
VoxGrid operates as a distributed network of independent storefronts, each serving the same core text-to-speech API infrastructure. This structure ensures that large SaaS teams can access the service through distinct regional or branding interfaces without compromising the underlying engine's consistency.
Each storefront functions as a self-contained billing and authentication boundary. While the API logic remains identical across the network, account management is isolated per site, allowing organizations to maintain separate usage profiles depending on their specific operational requirements.
Independent Storefronts
The network consists of multiple independent websites, such as ba11.info, each acting as a distinct storefront. This separation allows for localized branding and administrative independence while maintaining a unified technical backend for audio synthesis.
Teams can register accounts on any site within the network. The choice of storefront does not affect the quality of the generated audio or the pricing structure, which remains consistent across all nodes.
- Distinct branding per site
- Unified backend infrastructure
- No cross-site data mixing
Same API Core
All storefronts connect to the identical POST https://api.ba11.info/v1/audio/speech endpoint structure. Request shapes, voice presets, and language support are consistent regardless of which site you use to authenticate.
The underlying engine processes requests in the same queue, ensuring that performance characteristics like speed and latency remain uniform across the entire network, supporting predictable scaling for notification systems.
Site Specific Keys
Authentication keys are issued per site, meaning your API key on one storefront is distinct from another. This isolation simplifies security audits and allows teams to revoke access to one interface without affecting others.
Each account is tied to a specific site domain. If you switch storefronts, you will receive a new key, and the old one from the previous site becomes inactive immediately, ensuring clear audit trails for billing and usage.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Her consistent delivery helps users process important data quickly, especially in high-stress scenarios like payment failures or service disruptions.
23 languages
Any voice speaks any of these languages.
