Frequently asked questions
Who runs this site?
An independent team operates this storefront for the IVR Voice text-to-speech API. We are not a large corporation but a focused group helping product teams deploy TTS for call centers. Our goal is to provide a reliable, straightforward API without the complexity of legacy systems.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Our API endpoint mimics the OpenAI speech request shape for convenience, but we are a separate entity. We do not use OpenAI’s infrastructure or branding, and our pricing and features are entirely independent.
Where do voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These sources include LibriVox public-domain audiobook readings. We use these high-quality, legally cleared recordings to create the synthetic voices that power our API, ensuring a natural sound for your IVR applications.
Do you train on my data?
No. Your input text is used only to produce the specific audio file for that request. We do not use your data for training our models. Once the audio is generated and returned, the text is not retained for future model improvement or voice synthesis.
Do you store generated audio?
No. Generated audio is returned directly in the response and is not stored by us. We keep request metadata, such as time, character count, and status, strictly for billing purposes. Your actual audio files are not archived on our servers after delivery.
How do I contact support?
Support is available via email only. We do not offer live chat or phone support. You can reach our team through the contact page or by emailing us directly. We aim to respond to your inquiries promptly to help resolve any issues with your API usage.
Is there a phone number?
No, there is no phone number for IVR Voice. All support communication is handled via email. This allows us to maintain a focused, asynchronous support workflow that fits the needs of product teams and developers who prefer written records of their technical discussions and issues.
Do you have an SLA?
No, we do not offer a Service Level Agreement or uptime guarantee. Our API is designed for reliability, but we do not contractually guarantee specific availability percentages. We operate as an independent service, and while we strive for consistency, there is no formal SLA backing our operations.
Are you certified?
No, we do not hold certifications such as SOC 2, HIPAA, or GDPR certificates. We follow standard data practices, but we do not undergo external audits for these specific compliance standards. If you require specific certifications, please verify our data handling practices via our email support channel.
What is the team size?
We are an independent team, but we do not publish a specific headcount. Our structure is optimized for maintaining and improving the TTS API. We focus on engineering and support to ensure your IVR deployments run smoothly without the overhead of a large corporate organization.
Where is the company located?
We are a distributed, independent team without a single physical headquarters. As a cloud API provider, our location is less relevant than our infrastructure. We operate globally to serve product teams and call centers worldwide, ensuring low-latency access to our text-to-speech services regardless of your region.
Do you offer enterprise plans?
No, we do not offer enterprise contracts or dedicated seats. Our pricing is straightforward: $10 per million characters with no monthly plans or minimum spend. This model allows any team to scale usage up or down based on their actual call center volume without negotiating custom agreements.
Can I request a feature?
Yes, you can request features via email support. While we do not have a public roadmap, we listen to user feedback to guide development.
How do I report a bug?
Report bugs by emailing our support team. Include details like your API key, request ID, and the text used. Since we do not have a public issue tracker, email is the most direct way to ensure your report is seen and addressed by our engineering team promptly.
Who We Are
We are an independent team focused on delivering cloud text-to-speech for IVR and support bots. Our goal is to help product teams deploy synthetic audio fast enough for natural conversation flow, avoiding the latency of legacy systems.
We do not maintain a proprietary SDK, using standard HTTP endpoints compatible with the OpenAI SDK. This simplicity lets you integrate quickly using tools you already know.
Independent Team
We are not a subsidiary of a large tech brand. As an independent storefront, we make decisions based on what works for your workflow, not corporate roadmaps. We offer a straightforward API with transparent pricing and no hidden enterprise contracts.
Focus on Speed
Latency matters in call centers. Our API delivers synthetic audio quickly, allowing voices to respond in near real-time. Requests are processed sequentially, so under load a request may wait in a queue. Typical generation matches real-time speed for long texts, keeping your IVR conversations flowing naturally.
Product Led Growth
We let the API speak for itself. You can start with a free trial credit of $0.50 (about 50,000 characters) by signing in with Google. There are no monthly plans or minimum spends—just pay for what you use via USDT.
Voice Licensing
We built our voice presets using the LibriTTS-R dataset, which provides high-quality speech recordings from public domain audiobooks.
LibriTTS-R Source
Our eight voice presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are derived directly from licensed recordings in the LibriTTS-R dataset. By using these established recordings, we deliver consistent audio quality.
CC BY 4.0 License
The underlying audio data is licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This open license allows us to process and synthesize the speech while maintaining transparency about the origin of the voice models used in your calls.
Public Domain Audio
Many recordings in LibriTTS-R originate from LibriVox, featuring public domain audiobook readings. This foundation means our voices are built on content that is freely available for adaptation, ensuring a stable and legally clear base for your text-to-speech integration.
Data Policy
We use your input text strictly to generate the requested audio file. Once the synthesis is complete, the generated audio is returned in the response and is not stored on our servers for later retrieval or reuse.
No Training Data
Your input text is used only to produce the audio and is not used for training our models. We do not retain your input text for future model improvement.
No Storage of Audio
Generated audio files are returned in the response and are not stored persistently. Once you download the file, it is gone from our systems. We do not keep copies for backup or reuse.
Metadata Retention
Request metadata (time, characters, status) is kept for billing purposes. This ensures accurate charges and helps us monitor rate limits without retaining the actual content you processed.
Technology Stack
IVR Voice operates as a pure cloud API, designed specifically for the latency-sensitive environments of call centers and support bots. We deliver synthetic audio fast enough for natural conversation flow, ensuring your IVR systems remain responsive without the overhead of legacy infrastructure.
Cloud Based API
Our service is built entirely on the cloud, eliminating the need for on-premise hardware or data-center choices. You interact with a simple endpoint that processes requests sequentially, handling up to 4096 characters per request. This architecture keeps costs transparent and scalable, fitting seamlessly into your existing product workflows.
Standard HTTP
We use standard HTTP POST requests with JSON bodies, identical in shape to the OpenAI speech endpoint. This allows you to use the official OpenAI SDKs by simply changing the base_url to https://api.0000ff.info/v1. No custom client libraries are required to start generating audio from your text.
- Endpoint:
POST /v1/audio/speech - JSON body with
model,input,voice, andresponse_format - Bearer token authentication via
Authorizationheader
No Proprietary SDK
We do not maintain a dedicated SDK, mobile library, or WordPress plugin. Our API is self-contained and accessible via any standard HTTP client or the widely adopted OpenAI SDK. This reduces integration friction, allowing your team to use the tools they already know and trust for IVR integration.

Support and Contact
We believe in clear, asynchronous communication that respects your workflow. Our support team is dedicated to resolving technical questions efficiently without the noise of phone trees or waiting on hold.
Email Support Only
All inquiries are handled via email. This allows us to provide detailed, documented responses that you can reference later when integrating our API into your IVR systems.
No Phone Number
We do not maintain a phone line. Support is by email only.
Response Times
For urgent issues during integration, please include your API key and error logs in your initial message to help us diagnose the problem faster.
History and Mission
We built IVR Voice to solve a specific problem: legacy TTS systems were too slow for natural conversation flow. Product teams needed synthetic audio that arrived in time for real-time interaction without the latency of older infrastructure.
Our mission is to simplify deployment by providing a standard API that fits directly into existing call center workflows. We focus on delivering reliable, fast audio synthesis that supports the rhythm of human dialogue, ensuring your IVR feels responsive and clear.
Born from IVR Needs
We started because existing solutions couldn't match the speed requirements of modern support bots. By optimizing for low-latency delivery, we ensure that text-to-speech responses keep up with the pace of a real conversation, reducing wait times for callers.
- Optimized for real-time IVR workflows
- Low-latency audio delivery
- Designed for support bot integration
Simplifying TTS
We removed the complexity often found in enterprise speech solutions. Our API uses standard HTTP requests, so you can integrate it quickly using the same tools you already know, like the OpenAI SDK or simple curl commands.
By sticking to a straightforward model and voice selection process, we let your engineering team focus on building features rather than configuring speech engines.
- Standard HTTP endpoints
- No proprietary SDK required
- Easy integration with existing stacks
Transparent Pricing
We charge $10 per 1 million characters, with no hidden fees or monthly plans. This straightforward model means you only pay for what you use, making it easy to forecast costs for your IVR traffic.
There are no seats, no minimum spend, and no subscriptions. If a request fails, you aren't charged, ensuring you only pay for successful audio generation.
Our pricing is designed to be predictable and scalable, supporting everything from small pilot programs to high-volume call centers without surprise costs.
- $10 per 1 million characters
- No monthly plans or seats
- Pay only for successful requests
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This model scales naturally with your call volume, whether you handle a few hundred or millions of interactions monthly.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- curl documentation
- OpenAI API reference: create speech
- LibriTTS-R corpus (OpenSLR 141)
- IETF RFC 7845: Ogg Opus
- Node.js documentation
- LibriTTS-R paper (arXiv 2305.18802)
- Tether (USDT)
- MDN: Web Speech API
- Creative Commons Attribution 4.0
- W3C WAI: making audio and video accessible
- ISO 639 language codes
