Frequently asked questions
Who runs Narrata?
Narrata is an independent storefront for the Narrata text-to-speech API. We operate as a distinct entity, not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Our editorial team focuses on providing clear, factual information about our API capabilities, pricing, and data policies for educational and enterprise teams.
Are the voices owned by the site?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We do not claim ownership of the original source material. Our service generates synthetic audio using these licensed presets, and every generated file includes an inaudible watermark identifying it as synthetic speech.
Where do the voices come from?
Our eight voice presets are derived from licensed recordings in the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox. These sources provide the base audio data used to generate our voice presets, ensuring a consistent and compliant audio output for your educational content without requiring additional voice licensing.
Is my text data used for training?
No. Your input text is used exclusively to produce the requested audio file. We do not use your submitted text for training our models or improving the engine. Once the audio is generated and returned in the response, the input text is not stored for training purposes, ensuring your content remains private.
How long is my data kept?
We retain request metadata, including time, character count, and status, strictly for billing and usage verification purposes. The generated audio is returned in the response and is not stored on our servers after delivery. We do not keep your input text or the resulting audio files beyond what is necessary for the transaction.
How can I contact support?
Support is available via email only. We do not offer a phone number, live chat, or SLA. You can reach our team through the contact page or by emailing us directly.
Is there a phone number for support?
No, we do not offer a phone number for support. All customer service and technical inquiries are handled via email. This approach allows us to maintain detailed records of your requests and provide written responses that you can reference later. We do not have live chat or voice support channels.
Do you offer enterprise contracts?
No, we do not offer enterprise contracts, SLAs, or uptime guarantees. Our service is designed for self-service usage with no minimum spend or monthly plans. You pay only for what you use, with a simple per-character pricing model. There are no seats or custom enterprise agreements for large educational teams.
Who We Are
Narrata operates as an independent storefront for the Narrata TTS API, positioned specifically for enterprise learning and development teams and course producers. We provide a straightforward mechanism to generate consistent, compliant audio at scale for large educational content libraries, clarifying the technical and legal realities of AI voice generation.
Editorial Focus on LMS
Our editorial focus remains on the specific needs of the LMS industry. We address how large teams can deploy synthetic voices across extensive course libraries without legal risk, ensuring that the audio produced fits seamlessly into existing learning management systems.
Independent Storefront
We are not affiliated with OpenAI, ElevenLabs, or any other major brand. This site is a direct sales channel for the same cloud API used by developers who configure the base URL to https://api.c168s.info/v1. We handle the billing, key management, and voice presets directly, offering a transparent alternative for enterprise procurement without hidden subscriptions.
Voice Licensing and Sources
Our voices are built from licensed recordings in the LibriTTS-R dataset, available under the CC BY 4.0 license. This foundation allows us to offer eight distinct presets—such as Aria, Nova, and Atlas—without relying on proprietary synthetic models or celebrity voice designs.
Each preset originates from LibriVox public-domain audiobook readings, providing a consistent, natural baseline for educational content. Because the source material is public domain, we can distribute narration assets for large-scale LMS deployments without complex licensing overhead.
LibriTTS-R and CC BY 4.0
The Narrata engine uses the LibriTTS-R dataset, licensed under CC BY 4.0. This dataset provides speech samples that form the basis of our eight voice presets. Unlike custom voice cloning, these voices are fixed presets derived from established recordings.
This licensing structure ensures that your generated audio remains compliant for commercial and educational use. You benefit from clear legal boundaries, knowing the underlying voice data carries a standard open license rather than restrictive proprietary terms.
- Based on the LibriTTS-R dataset
- Licensed under Creative Commons BY 4.0
- Applies to all eight voice presets
LibriVox Public Domain
The recordings used to train our voice models come from LibriVox, a collection of public-domain audiobooks read by volunteers. Since these recordings are in the public domain, they can be freely used and modified.
This source gives our voices a natural, human-like quality without the need for expensive exclusive rights. It allows us to provide reliable audio for course producers and L&D teams.
- Source material from LibriVox
- Public-domain audiobook readings
- Natural human-like quality
Data Privacy and Usage
When you send text to the Narrata API, the input is processed solely to generate the corresponding audio file. We do not use your content to train or improve our underlying speech models, ensuring that your educational material remains distinct from our training data.
Input Text Not Trained On
Your input text is used exclusively for synthesis and is not added to our training datasets. This approach supports compliance for sensitive corporate or academic content, as the voice engine does not learn from your specific library of courses.
Audio Not Stored
Generated audio files are returned directly in the API response and are not retained on our servers after delivery. We keep only request metadata—such as timestamp, character count, and status—for billing purposes, ensuring no long-term storage of your creative assets.
Billing and Metadata Retention
Narrata charges $0.01 per 1,000 characters, including spaces and punctuation. Failed requests are free, with the charge returned in full. Accounts start with a $0.50 trial credit valid for seven days when signed in with Google; email accounts begin without credit. There are no monthly plans, subscriptions, or minimum spend requirements.
Billing relies on request metadata, which includes the timestamp, character count, and status code. This data is retained solely for accurate billing and dispute resolution. Once a top-up is completed via USDT (TRC-20), the balance updates automatically, and funds never expire.
Request Metadata for Billing
We keep only the metadata necessary to verify usage and process refunds for failed syntheses. This includes the request time, input length, and outcome. We do not store the audio files or the original text after delivery.
- Timestamp of request
- Character count billed
- Request status (success/fail)
No Long-Term Audio Storage
Generated audio is returned directly in the API response and is not stored on our servers. Input text is used exclusively to produce the audio and is not used for training models. Only the minimal metadata required for billing remains in our systems.

Support and Contact
Support for Narrata is handled exclusively through email. We prioritize clear, documented responses over real-time availability, ensuring that every query receives a thorough review from our team. This approach allows us to maintain high-quality support for our enterprise L&D clients without the overhead of live agents.
Our channel is limited to email; we do not offer phone support or live chat. If you require immediate assistance, please review our documentation first, as most technical questions regarding API integration and voice selection are covered there.
Email Support Only
We prioritize clear, documented responses over real-time availability, ensuring that every query receives a thorough review from our team. This approach allows us to maintain high-quality support for our enterprise L&D clients without the overhead of live agents.
Our channel is limited to email; we do not offer phone support or live chat. If you require immediate assistance, please review our documentation first, as most technical questions regarding API integration and voice selection are covered there. We aim to respond to all inquiries within one business day.
No Phone or Live Chat
We do not maintain a call center or instant messaging widget. This structure keeps our operational costs low, allowing us to pass those savings on to our customers in the form of competitive character-based pricing.
Limitations and Transparency
Our infrastructure processes requests sequentially, which means generation speed depends on current load. While typical performance mirrors real-time speech, bursts of activity may introduce queueing delays. We do not promise specific latency thresholds or continuous availability windows, as our service operates without formal service-level agreements.
No SLA or Uptime Guarantee
We do not offer an SLA or uptime guarantee. Requests are processed in order, so high demand may temporarily extend synthesis time beyond the usual real-time ratio. If synthesis fails, you are not charged, but we do not compensate for downstream production delays caused by these queues.
- No formal uptime commitment
- Requests processed sequentially
- Queueing possible during peak load
No Certifications
We do not hold specific industry certifications such as SOC 2 or HIPAA, nor do we maintain GDPR-specific certificates. Our data policy is straightforward: input text is used solely for synthesis, and generated audio is not stored long-term. We prioritize transparency over administrative compliance badges.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This preset is particularly effective for keeping learners engaged in short modules or promotional training content.
23 languages
Any voice speaks any of these languages.
