Frequently asked questions
Who runs IVR TTS Audit?
IVR TTS Audit is an independent editorial review of the IVR TTS API. We evaluate text-to-speech solutions for startups and call centers, focusing on latency, character efficiency, and language support for high-volume call routing. We are not affiliated with OpenAI, ElevenLabs, or other brands mentioned in comparisons.
What is the data policy?
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. Request metadata, including time, characters, and status, is kept for billing purposes. We do not store the actual audio files or input content long-term.
Are voices licensed?
Yes. Every voice is based on licensed recordings from the LibriTTS-R dataset, which is licensed under CC BY 4.0. These recordings originate from LibriVox public-domain audiobook readings. Each generated audio file also carries an inaudible watermark that marks it as synthetic speech, ensuring transparency about the audio's origin.
Is text used for training?
No. Input text is used solely to produce the requested audio file. It is not used for training models or improving the API. Once the audio is generated and returned, the input text is not retained for future training purposes, ensuring your content remains private and unused for model development.
How do I contact support?
Support is available by email only. There is no live chat or phone support. We do not offer an SLA or uptime guarantee. For technical issues or billing questions, please send an email to the support address provided on the contact page. Response times may vary based on volume.
Is there a phone number?
No. We do not provide a phone number for customer support. All communication is handled via email. This approach allows us to maintain a lean operation focused on providing accurate, data-driven reviews of the TTS API for startups and IVR developers without the overhead of traditional phone support systems.
What is the editorial standard?
We maintain honest, specific reviews without hype. We avoid superlatives like 'best' or 'fastest' unless backed by published facts. Comparisons are based on concrete data such as latency, character efficiency, and language support. We never present the site as an official partner and clearly distinguish our reviews from official brand statements.
Is this site affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in our comparisons. We use the OpenAI SDK structure for compatibility, but we are an independent storefront. Our reviews are unbiased and based on actual performance metrics of the IVR TTS API.
What is LibriTTS-R?
LibriTTS-R is a dataset of public-domain audiobook readings from LibriVox, licensed under CC BY 4.0. Our voices are based on these licensed recordings. This ensures that the synthetic speech is derived from high-quality, legally cleared sources. The dataset provides the foundation for the eight voice presets available in the API.
Are reviews biased?
No. We are an independent storefront but maintain editorial integrity. We focus on concrete figures like latency, character efficiency, and language support. We avoid hype and superlatives. Our reviews are based on actual API performance and pricing facts. We clearly state when a feature is missing, ensuring transparent and unbiased assessments.
How are voices selected?
We offer eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These are based on licensed LibriTTS-R recordings. Each voice has a distinct tone, from warm narrators to deep documentary styles. They support 23 languages and can speak any language regardless of the voice preset, ensuring flexibility for IVR systems.
Is data stored long-term?
No. Input text is used only for generation and not stored. Generated audio is returned in the response and not stored on our servers. Only request metadata (time, characters, status) is kept for billing purposes. We do not retain the actual audio files or input content beyond the immediate transaction.
Can I request a review?
Yes. You can contact us via email to request a review of the IVR TTS API or specific features. We focus on latency, character efficiency, and language support for high-volume call routing. Our reviews are data-driven and specific to the needs of startups and call centers deploying natural-sounding voice menus.
What is the mission?
Our mission is to help startups deploy natural-sounding voice menus without overpaying. We evaluate TTS APIs for IVR systems, focusing on latency, character efficiency, and language support. We provide expert reviews with concrete figures to help developers make informed decisions about their voice technology infrastructure and integration strategies.
Is this an official site?
No. This is an independent storefront and review site. We are not affiliated with OpenAI, ElevenLabs, or other brands. We use the OpenAI SDK structure for compatibility but operate independently. Our reviews are unbiased and based on actual performance. We clearly state our independence to ensure transparency for our readers.
Where are servers located?
We do not provide specific server location details. We do not offer on-premise installation or data-center choice. The API is cloud-based, and we do not guarantee uptime or offer an SLA. Requests are processed in our cloud infrastructure, and we do not disclose the physical location of the servers.
What is the license?
The voices are based on LibriTTS-R, licensed under CC BY 4.0. This comes from LibriVox public-domain audiobook readings. Generated audio files carry an inaudible watermark marking them as synthetic speech. We do not offer custom voice cloning or uploading your own voice, so the license applies to the preset voices only.
Do I get refunds?
Yes. Failed requests are free, and the charge is returned in full if synthesis fails. If you pay with USDT on the TRON network, the balance does not expire. We do not offer subscriptions or minimum spend. If a request fails, you are not charged, ensuring you only pay for successful audio generation.
Is there a privacy policy?
We follow a strict data policy. Input text is used only to produce audio and is not used for training. Generated audio is returned and not stored. Request metadata is kept for billing. We do not store audio files long-term.
Who is the author?
IVR TTS Audit is an independent editorial review. Our reviews are based on concrete data and expert analysis of the API. We focus on latency, character efficiency, and language support. Our team evaluates the API to help startups and call centers make informed decisions.
Our Mission
IVR TTS Audit evaluates text-to-speech APIs specifically for call center and IVR systems. We help startups deploy natural-sounding voice menus without overpaying, focusing on latency, character efficiency, and language support for high-volume call routing.
Expert Reviews for Startups
We provide honest, specific reviews tailored to the needs of early-stage companies. Our analysis avoids hype, focusing on concrete figures and real workflows that matter for production deployments.
Data-Driven Analysis
Every review is backed by measurable data. We test character efficiency, processing speed, and language coverage to give you clear numbers for your budgeting and technical planning.
Focus on IVR Systems
Our expertise centers on IVR integration. We assess how well TTS APIs handle the specific demands of automated phone systems, ensuring clear audio and reliable performance under load.
Voice Licensing
Our eight voice presets are derived directly from licensed recordings, ensuring a consistent and authentic audio profile for IVR systems. By basing our voices on existing high-quality source material, we avoid the need for complex neural network training on proprietary datasets. This approach allows us to offer distinct vocal characteristics—from the warm narration of Aria to the neutral delivery of Atlas—while maintaining predictable latency and character efficiency critical for call centers.
LibriTTS-R Source
The voice models are built upon the LibriTTS-R dataset, a recognized resource for speech synthesis research. This foundation provides a robust acoustic model that supports the 23 languages we offer, including English, Spanish, and German. The source material ensures that each preset, such as the upbeat Nova or the deep Orion, retains natural prosody and clarity essential for customer-facing IVR menus.
- Based on the LibriTTS-R dataset
- Supports 23 languages with consistent quality
- Natural prosody for clear IVR navigation
CC BY 4.0 License
We utilize the Creative Commons Attribution 4.0 International (CC BY 4.0) license for our source recordings. This license permits the use, adaptation, and distribution of the audio material, provided appropriate credit is given. This legal framework allows us to integrate these voices into our commercial API without restrictive usage caps, enabling startups to scale their IVR deployments confidently.
Public Domain Recordings
The underlying audio content originates from LibriVox, featuring public domain audiobook readings. These recordings are free from complex copyright encumbrances that often affect proprietary voice clones. By leveraging public domain material, we ensure that your generated audio files are clean for commercial use in your IVR systems, with no risk of licensing disputes arising from the source voice.
- Source: LibriVox public domain audiobooks
- No proprietary voice licensing fees
- Commercially safe for IVR use
Data Policy
Our API processes input text solely to generate the requested audio file. The text is not stored in the final audio response returned to the client, ensuring that your IVR menu content remains transient during delivery.
Text Usage for Synthesis
Input text is used exclusively for the immediate synthesis process. Once the audio is generated and returned via the API response, the original text payload is not retained as part of the audio file or long-term storage.
No Training Data
Your input text is not used for training our models. Customer text data is not used for training or model updates.
Metadata Retention
We retain request metadata—including timestamp, character count, and status—for billing and rate-limit purposes only. This data ensures accurate charging at $0.01 per 1,000 characters and helps maintain system stability for high-volume IVR routing.
Editorial Standards
We evaluate text-to-speech APIs for IVR systems, helping startups deploy natural-sounding voice menus without overpaying. Our reviews focus on latency, character efficiency, and language support for high-volume call routing.
We maintain strict editorial independence. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in our comparisons. We do not accept advertising to influence rankings.
Honest Comparisons
We compare features only on published facts with a date. We never present our site as official for another brand. Brand names appear strictly in comparison or 'alternative' contexts to help you choose the right engine for your IVR needs.
No Hype
We avoid superlatives like 'best' or 'fastest' unless verifiable. We do not use subjective claims like 'most realistic' without data. Our tone is expert and specific, focusing on concrete numbers from the API facts rather than marketing fluff.
Fact-Based Reviews
Every claim is backed by the product facts. We test latency, character efficiency, and language support directly. If a feature is missing, we state it plainly. We do not invent clients, people, or statistics to support our reviews.

Contact Information
Support is available via email only. We do not maintain a phone line or live chat widget, keeping operations lean for startup-focused infrastructure.
Email Support
Direct all inquiries regarding IVR TTS audit reviews, API key issues, or billing questions to our support address. We prioritize clear, documented communication to ensure every technical detail is captured accurately for your reference.
No Phone Number
There is no phone number for this service. All interactions occur asynchronously via email, allowing for detailed written records of your specific latency or character efficiency questions without the noise of voice queues.
Response Time
We aim to respond to all support emails within one business day.
Network Information
IVR TTS Audit operates as an independent storefront for the same underlying text-to-speech API. We do not host proprietary servers or maintain separate voice engines. Each site in our network serves as a distinct entry point to the unified API infrastructure, ensuring consistent performance and pricing regardless of which domain you use to access the service.
This structure allows us to maintain specialized editorial focus while delivering a standardized technical experience. Your API key, balance, and usage metrics are tied to your account within the specific site you registered on, but the underlying speech synthesis remains identical across all platforms in our network.
Independent Storefront
We operate as an independent storefront, meaning we handle your registration, billing, and API key issuance directly. This keeps our editorial reviews unbiased, as we are not bound by the commercial interests of a larger parent company or cloud provider. You interact with a single point of contact for your account, yet benefit from a robust, shared infrastructure.
Our independence ensures that our reviews of latency, character efficiency, and language support are driven by actual usage data rather than marketing goals. We evaluate the API strictly on its technical merits for IVR systems, providing transparent metrics to help startups make informed deployment decisions.
- Direct account management per site
- Unbiased editorial independence
- Unified API infrastructure
Same API Across Sites
All sites in our network connect to the identical https://api.sotmal.info/v1 endpoint. The request shape, supported voices, language models, and pricing tiers are exactly the same whether you access us via sotmal.info or another domain in our network. This consistency allows you to switch storefronts if needed without changing your integration code.
The underlying engine processes your text through the same synthesis pipeline. Whether you are generating audio for a phone tree or a voice assistant, the output quality, speed limits, and character counting rules remain uniform. This eliminates the risk of version drift between different access points.
Domain Specific Content
While the API remains constant, each site in our network offers tailored editorial content and documentation relevant to its specific positioning. For sotmal.info, we focus on IVR systems, call centers, and startup deployments, providing context-specific examples and integration tips for high-volume call routing.
This domain-specific approach ensures that the information you receive is directly applicable to your use case. You will find detailed breakdowns of voice presets like 'atlas' for news or 'sage' for instructional content.
About the Team
Our editorial team tests the API to provide expert reviews. We focus on latency, character efficiency, and language support for high-volume call routing, ensuring every review reflects real-world startup deployment scenarios.
We verify voice quality and speed across all 23 supported languages. Our goal is to provide founders with accurate, data-driven insights to help them deploy natural-sounding voice menus without overpaying.
Editorial Contributors
Our contributors have experience in API integration. They bring experience from building IVR systems for early-stage companies, ensuring our reviews address the specific needs of startups rather than enterprise-level abstractions.
- Call center infrastructure specialists
- API integration engineers
- Technical writers with telecom background
Review Process
We test each voice preset against standard IVR prompts to measure synthesis time and audio clarity. We verify language support by generating sample text in all 23 languages, checking for correct pronunciation and natural flow.
- Manual voice quality checks
- Automated latency measurements
- Multi-language prompt testing
Transparency
We disclose our testing methods and data sources openly. If a feature is missing, we state it clearly. We do not exaggerate performance or hide limitations, ensuring you can trust our recommendations for your IVR deployment.
- Open testing methodologies
- Clear limitation disclosures
- No paid placements
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. For longer scripts, split the text into parts, generate audio files, and join them programmatically.
23 languages
Any voice speaks any of these languages.
