Frequently asked questions
Who runs the Narrivo website?
This is an independent storefront for the Narrivo TTS API. The site is operated by the team behind the API, providing direct access to the service without being an official subsidiary of any major tech brand.
Are the voices copyrighted?
Q: Are the voices copyrighted? A: The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. The generated audio files are delivered to you for use in your applications.
Is the audio synthetic?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech.
Do you store my text?
No. Input text is used only to produce the audio and is not used for training. The generated audio is returned in the response and is not stored on our servers after delivery.
How long is metadata kept?
Request metadata, including time, characters, and status, is kept for billing purposes.
Do you have a physical office?
We do not list a physical office address. As an independent API provider, we operate remotely. Support is available by email only.
Can I request a specific voice?
You can choose from eight curated presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, or Orion. You select the voice by name in your API request; we do not offer custom voice cloning or design.
Do you offer enterprise contracts?
No. We do not offer enterprise contracts, SLAs, or uptime guarantees. Our model is designed for startups and developers who need a simple, pay-as-you-go API. There are no monthly plans, seats, or minimum spend requirements.
Is there an SLA?
No, there is no Service Level Agreement or uptime guarantee. Requests are processed one after another, so under load a request may wait in a queue.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API endpoint shape is similar to OpenAI’s, allowing you to use their SDKs by changing the base URL.
Do you have a mobile app?
No, we do not have a mobile app or a browser extension. We provide a REST API that you integrate directly into your own applications. You can use the official OpenAI SDKs or plain HTTP to connect your app to our API.
Can I export my API key?
Yes. You can view your active key on the /get-api-key/ page. You can also issue a new key at any time, which immediately stops the old one.
Is support available 24/7?
No, we do not offer 24/7 support or live chat. Support is available by email only. There is no phone number for direct contact.
Do you sell user data?
No, we do not sell user data. Input text is used only for synthesis and not for training. We keep request metadata for billing.
Who We Are
Narrivo is an independent storefront for the same text-to-speech API used across our network. We are not affiliated with OpenAI, ElevenLabs, or any other major voice brand. Our editorial team curates the interface and documentation to help startup product teams integrate human-sounding voice into their apps and notifications without hiring voice actors.
We focus on providing a simple API and curated voices designed for clear, natural user experiences. By keeping our structure lean, we avoid the overhead of enterprise contracts or complex billing, allowing you to pay only for what you use.
Editorial Team
Our small, dedicated editorial team maintains the documentation and ensures the API remains straightforward for developers. We handle the curation of voice presets and language support so your team can focus on building product features rather than managing voice infrastructure.
Independent Storefront
Narrivo operates as an independent storefront for the underlying TTS API. This means we provide a distinct billing and account experience without the brand baggage of larger providers. You get the same engine and voice presets, but with a cleaner, startup-friendly interface.
Startup Focus
We built Narrivo for startups that need to integrate voice quickly. Our pricing is transparent ($0.01 per 1,000 characters), and our API matches the familiar OpenAI request shape. This reduces integration time, letting you add notifications and UI voices in days, not weeks.
Our Voices
We provide eight curated voices built from licensed recordings in the LibriTTS-R dataset. These voices, ranging from warm narrators to energetic promoters, are engineered for clear, natural user experiences in startup apps and notifications.
LibriTTS-R Source
Our voices are based on licensed recordings from the LibriTTS-R dataset.
CC BY 4.0 License
The underlying audio data is licensed under CC BY 4.0.
Public Domain Recordings
Many of the source recordings originate from LibriVox public-domain audiobook readings.
Data Policy
Narrivo treats your data with minimal footprint. Your input text is used only to produce the audio and is not used for training. This ensures that your unique product copy or user notifications remain private and are not repurposed to improve our models.
Generated audio is returned in the response and not stored on our servers. Once you receive the file, we have no copy of it. This transient approach keeps your voice outputs secure and aligned with strict privacy standards for startup apps.
No Training Data
Your input text is used only to produce the audio and is not used for training. We do not ingest your strings into our datasets, preserving the exclusivity of your content.
No Storage
Generated audio is returned in the response and not stored on our servers. We do not keep copies of your synthesized clips, ensuring your voice outputs remain ephemeral and secure.
Metadata Retention
Request metadata (time, characters, status) is kept for billing. We retain only the data necessary to verify usage and process charges, discarding excess information once billing is settled.
Technical Limits
We prioritize simplicity and predictability in our API design. By focusing on standard HTTP requests that return complete audio files, we ensure straightforward integration for startup teams who need reliable notifications without managing complex real-time streams.
No Streaming
The API returns complete audio files upon request completion. We do not offer WebSocket or streaming endpoints for real-time partial audio delivery.
No SSML
We do not support Speech Synthesis Markup Language (SSML). There are no built-in phoneme dictionaries or custom pronunciation lexicons. Control is limited to the standard speed parameter, which ranges from 0.25 to 4.0.
No Custom Cloning
We do not offer custom voice cloning for customers, so you cannot upload your own voice to generate speech. The eight curated presets are based on licensed recordings from LibriTTS-R and are available as-is.

Support Channels
We keep support simple and reliable. You can send us a message at [email protected]. We handle all technical questions, billing inquiries, and account issues through this single channel.
Email Only
We handle all technical questions, billing inquiries, and account issues through this single channel.
No Live Chat
We don’t offer live chat widgets. This allows us to maintain thorough, documented responses rather than quick, fragmented chats.
No Phone Number
There is no phone support line. This fits our remote-first, async nature and keeps our operational costs low. You can always reach us by email.
Contact Us
Reach our support team directly by sending an email to [email protected]. This is the single, dedicated channel for all technical and billing inquiries, ensuring your questions are tracked and resolved without the noise of other communication streams.
We aim to reply to all emails within one business day. Since we do not have a live chat or phone support, email remains our most reliable way to resolve specific technical or billing questions.
Email Address
Reach our support team directly by sending an email to [email protected]. This is the single, dedicated channel for all technical and billing inquiries, ensuring your questions are tracked and resolved without the noise of other communication streams.
Response Time
We aim to reply to all emails within one business day. Since we do not have a live chat or phone support, email remains our most reliable way to resolve specific technical or billing questions.
Location Independence
We operate independently of major tech hubs. This structure keeps our costs low and our API pricing straightforward.
None
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. You can generate thousands of unique notifications daily, ensuring your product feels dynamic and responsive to user needs.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- curl documentation
- W3C WAI: making audio and video accessible
- MDN: Web Speech API
- IETF RFC 7845: Ogg Opus
- Node.js documentation
- LibriTTS-R corpus (OpenSLR 141)
- TRON developer hub: TRC-20
- LibriTTS-R paper (arXiv 2305.18802)
- Creative Commons Attribution 4.0
- LibriVox public-domain audiobooks
- OpenAI API reference: create speech
