Frequently asked questions
Are you affiliated with Amazon?
No. We are an independent storefront for the IVR Switch TTS API. We are not affiliated with Amazon, Google, Microsoft, or any other brand mentioned in comparisons. Our platform operates separately from these major cloud providers.
Who owns the voice recordings?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. We use these sources to generate synthetic speech for your API requests.
Do you sell user data?
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 for billing purposes only.
Is there a phone support number?
No. We do not have a phone number or live chat. Support is provided by email only. You can reach us through the contact page on our website for any questions or issues.
Do you have an office?
We are an independent storefront and do not claim a physical office location. Our operations are managed digitally to keep things simple and transparent for indie developers and small call center teams.
Can I request a new voice?
No. We do not offer custom voice design or voice cloning. You can choose from our eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. Each has a specific tone and style.
Is the API open source?
No. We do not provide an official SDK of our own. You can use the official OpenAI SDKs by changing the base URL, or use plain HTTP requests.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. Otherwise, we do not offer traditional refunds. Your balance does not expire, so you can use it whenever you need.
How do I report a bug?
You can report bugs via email. Since we do not have phone support or live chat, email is our primary channel for handling issues, questions, and feedback from our users and developers.
Is the site secure?
Your API key is protected via Bearer authentication. We do not claim specific certifications like SOC 2 or HIPAA.
Do you use cookies?
Can I use the API for commercial use?
Yes. You can use the generated audio for commercial purposes. We just ask that you pay for the characters used.
Is there a privacy policy?
We maintain a privacy policy on our site. It details how we handle your input text, metadata, and account information. We do not store generated audio or use input text for training models.
Who is the editor?
Our content is managed by the team behind IVR Switch to ensure accuracy and clarity for our developer audience.
Who We Are
We are an independent storefront for the IVR Switch text-to-speech API, not a large corporation. Our small team of developers and writers understands the specific pain points of legacy TTS providers and aims to simplify integration for indie developers and small call center teams.
Independent editorial team
We operate as a focused group dedicated to clarity. We built this platform to provide a straightforward, transparent API without the bloat of enterprise giants. Our goal is to help you migrate from legacy systems with minimal friction.
Focus on developer experience
We prioritize the developer workflow above all else. By matching the OpenAI SDK request shape, you can swap in high-quality voices with a single line of code change. Our documentation and tools are designed to get you from sign-up to generated audio quickly.
No affiliation with major brands
IVR Switch is an independent storefront. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. While we use similar API structures for convenience, our engine, voices, and pricing are entirely our own. We do not claim to be any other brand.
Voice Licensing Sources
Our voice presets are built on licensed recordings from the LibriTTS-R dataset, derived from LibriVox public-domain audiobook readings. This foundation provides high-quality speech.
LibriTTS-R dataset usage
We use the LibriTTS-R dataset as the core source for our eight voice presets. Each voice, from Aria to Orion, is based on licensed recordings originally sourced from LibriVox.
CC BY 4.0 license details
The underlying data is licensed under CC BY 4.0. This allows us to integrate these voices into our API while maintaining transparency about the origin of the synthetic audio you generate.
LibriVox public domain origins
LibriVox provides public-domain audiobook readings, which we process to create our distinct voice profiles.
- Based on LibriVox public-domain audiobook readings
- Licensed under CC BY 4.0
- Used for all 8 voice presets
Data Privacy Policy
We prioritize your data’s privacy by ensuring your input text is used exclusively for the immediate production of audio files. We do not use your input text for training.
Once the synthesis is complete, the generated audio is returned in the response and is not permanently stored on our servers.
Input text not used for training
Your source text is processed solely to generate the requested audio. We do not use your input scripts to train or fine-tune our TTS models, ensuring your unique content remains distinct from our training data.
Audio not stored after response
Generated audio files are returned directly in the API response and are not permanently stored on our infrastructure. This minimizes the risk of long-term data retention issues for your call center or IVR applications.
Metadata kept for billing
We retain request metadata, including the timestamp, character count, and status, strictly for billing and usage tracking purposes. This ensures accurate charging based on your actual usage without storing the audio content itself.
Technical Limits and Honesty
We build for developers who value transparency over marketing fluff. IVR Switch is an independent storefront, not a subsidiary of a major tech giant. We don’t promise 99.99% uptime because we don’t offer SLAs.
No SLA or uptime guarantee
Our infrastructure is reliable, but we don’t contractually guarantee it. You use the API at your own risk regarding availability.
- No financial credits for downtime
- No contractual uptime guarantees
- Simple, flat pricing model
No enterprise contracts available
We are optimized for indie developers and small call center teams. We do not offer custom enterprise agreements or negotiated volume discounts. If you need a custom SLA, you might be looking for a larger provider.
- Standard terms only
- No custom negotiations
- Self-service model
Processing may queue under load
Requests are processed sequentially. If many users are generating audio simultaneously, your request may wait in a queue before synthesis begins. This means generation might take longer than the typical real-time speed during peak hours.
- Sequential processing
- Possible queue delays
- No priority tiering

Contact and Support
Support is by email only.
Email support only
Our primary and only channel for assistance is email.
No live chat or phone
We do not offer live chat widgets or phone numbers. This keeps our overhead low and allows us to focus resources on maintaining the API infrastructure and keeping prices transparent for indie developers and small call center teams.
Response time expectations
Mission Statement
We started IVR Switch because building voice interfaces shouldn’t require negotiating enterprise contracts or waiting weeks for API keys. Our goal is to give indie developers and small call center teams a reliable, straightforward tool that just works. We focus on the developer experience, ensuring you can swap in high-quality voices with a single line of code change.
Simplifying TTS for indie devs
We help small teams use a transparent API that fits into their existing workflows without friction. By matching the OpenAI request shape, you can use familiar SDKs and integrate speech synthesis quickly, regardless of your tech stack.
- OpenAI-compatible endpoint structure
- No custom SDKs to learn
- Quick integration for indie projects
Transparent pricing models
Our pricing is simple: $0.01 per 1,000 characters, with no monthly plans, seats, or hidden fees. You pay only for what you use, with no minimum spend required.
- $10 per 1 million characters
- No monthly plans
- No hidden fees
Empowering small call centers
We help small teams use a transparent API. This approach lets you scale voice capabilities without the overhead of legacy providers, giving you full control over your audio generation costs and performance.
- No enterprise contracts
- Scalable per-character pricing
- Full control over costs
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Her gentle cadence helps complex information land clearly, reducing the need for callers to ask for repetition during onboarding or support calls.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- ISO 639 language codes
- FFmpeg documentation
- LibriTTS-R paper (arXiv 2305.18802)
- LibriTTS-R corpus (OpenSLR 141)
- OpenAI API reference: create speech
- LibriVox public-domain audiobooks
- IETF RFC 7845: Ogg Opus
- Node.js documentation
- Tether (USDT)
- W3C WAI: making audio and video accessible
- Creative Commons Attribution 4.0
