Frequently asked questions
What does 'realistic human voice' mean for TTS?
Q: What does 'natural voice' mean for TTS? A: Our eight presets are designed for clear, natural user experiences without sounding robotic. They are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark marking it as synthetic speech. We do not offer custom voice cloning or emotion tags, but our voices are optimized for clear, natural integration into startup apps and notifications.
Which voices work best for app notifications?
Q: Which voices are recommended for app notifications? A: We recommend Milo (friendly, conversational) or Felix (energetic, promo). These voices are optimized for clarity and quick comprehension. You can adjust the speed between 0.25 and 4.0 to ensure the audio fits perfectly within your app’s interface without overwhelming the user with long durations.
How many languages does the API support?
The API supports 23 languages, including English, Spanish, French, German, Japanese, and Hindi. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses it from the script, defaulting to English for Latin text.
Do you support Hindi text to speech?
Yes, Hindi is one of our 23 supported languages. You can use any of the eight voice presets to generate Hindi audio. Simply set the language parameter to 'hi' in your request to ensure correct pronunciation and natural intonation for your startup’s users.
Can I use the OpenAI SDK with your API?
Yes, our endpoint shape matches the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.playbd4.com/v1 and using your Narrivo API key. This allows for easy integration into your existing codebase without learning a new library.
How much does it cost per character?
The price is $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, and the charge is returned in full if synthesis fails. There are no monthly plans or minimum spends.
Is there a free trial available?
Yes, signing in with Google gives you $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. You can top up your balance with USDT on the TRON network at any time.
Do you offer voice cloning for startups?
No, we do not offer custom voice cloning or uploading your own voice. Our eight presets are based on licensed recordings from LibriTTS-R and LibriVox. If you need a specific voice, you can choose from our curated list of female and male presets designed for clarity.
How fast is the audio generation?
Generation is roughly real time on long texts, processing about 25 characters per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. The rate limit is 60 requests per minute.
What formats can I receive the audio in?
You can receive audio in mp3, wav, opus, flac, or pcm formats. Simply specify your preferred response_format in the JSON body of your POST request to /v1/audio/speech. This flexibility allows you to choose the balance between quality and file size for your app.
Is my input text stored after generation?
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, such as time, characters, and status, solely for billing purposes and account management.
Can I cancel my subscription anytime?
No, we do not have subscriptions or monthly plans. You pay as you go with a balance that does not expire. You can top up with USDT whenever needed. There are no minimum spends or contracts, so you can stop using the API at any time.
Do you have an SLA for uptime?
No, we do not offer an SLA or uptime guarantee. We also do not provide enterprise contracts or certifications like SOC 2 or HIPAA. Support is by email only, with no phone number or live chat. We aim for reliability but do not guarantee specific uptime percentages.
How do I top up my balance with USDT?
Top up using USDT on the TRON network (TRC-20) only. The minimum top-up is $5. Credits are added automatically within minutes after your transfer is confirmed. We do not accept cards, PayPal, or invoices. You can manage your balance and view your API key on the dashboard.
First request
curl
curl https://api.playbd4.com/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Why Startups Choose Natural Voices
Modern app users expect clear, engaging audio rather than robotic monotone. Natural voices reduce cognitive load, helping users retain information faster and stay engaged with your product’s notifications or onboarding flows.
By replacing generic TTS with human-sounding speech, you create a more pleasant experience that encourages users to listen rather than skip, directly supporting better retention rates for audio-driven features.
Better User Retention
Listeners retain more information when audio sounds natural. Clear, expressive voices keep users engaged with long-form notifications or educational content, reducing drop-off rates in your app.
- Higher completion rates for audio notifications
- Reduced cognitive load for users
- Improved retention for onboarding flows
Clear Notifications
Startups use natural voices for urgent alerts, reminders, and status updates. Clear articulation ensures critical messages are understood instantly, whether the user is commuting or working.
- Instant understanding of urgent alerts
- Clear status updates without visual attention
- Reduced misinterpretation of critical info
Brand Personality
Your app’s voice defines its character. Choose from warm narrators, upbeat energizers, or calm instructors to match your startup’s unique tone and build a consistent brand identity.
- Consistent brand tone across features
- Curated voices for different moods
- Distinctive audio identity
Curated Voice Catalog
Narrivo’s voice catalog is curated specifically for startup interfaces, ensuring every notification and in-app message sounds human without the cost of hiring actors. Our eight presets cover the full spectrum of user experience needs, from gentle reminders to urgent alerts.
Each voice is built from licensed recordings, offering distinct personalities that help your brand stand out. Whether you need a warm narrator for onboarding flows or a deep documentary-style voice for long-form content, we have a preset ready for your app.
Warm Narrators
Voices like Aria and Luna bring a soft, storytelling quality to your app. They are perfect for onboarding sequences, help tips, or calming notification sounds that guide users without feeling robotic.
Aria’s clear, warm tone works well for educational content, while Luna’s softer delivery suits evening modes or wellness apps where a gentle presence is preferred.
- Aria: Warm, clear narrator for guides.
- Luna: Soft, storytelling voice for tips.
Energetic Promos
For sales, updates, or time-sensitive alerts, Felix and Milo deliver with bright, upbeat energy. These voices grab attention without being jarring, making them ideal for promotional notifications or feature announcements.
Felix brings an energetic, promo-ready tone, while Milo offers a friendly, conversational style that feels like a peer rather than a machine reading a script.
- Felix: Energetic, promo-ready tone.
- Milo: Friendly, conversational style.
Calm Instructions
Clarity is key for complex tasks. Sage provides a calm, instructional voice that helps users follow multi-step processes without confusion. Atlas offers a neutral, news-like tone for straightforward data readouts.
Use Sage for step-by-step tutorials or settings explanations. Atlas is suitable for financial updates, status reports, or any content where neutrality and clarity are prioritized over personality.
- Sage: Calm, instructional guidance.
- Atlas: Neutral, news-style clarity.
Global Reach with 23 Languages
Narrivo supports 23 languages, allowing startups to scale their voice interfaces globally without managing separate voice assets. Any of the 8 curated voices can speak any supported language, ensuring consistent brand tone across regions. If the language isn't specified, the system guesses from the script, though setting it explicitly is recommended for non-English Latin text.
English & Hindi
English remains the default for Latin-script text, but Hindi is fully supported for emerging markets. Both voices maintain their distinct character, whether delivering notifications or storytelling.
bullets
European Languages
Support includes German, French, Spanish, Italian, Dutch, Portuguese, Swedish, Danish, Norwegian, Finnish, Polish, Russian, Greek, and Turkish. This covers most major Western and Central European markets, enabling localized customer support and in-app guidance.
bullets
Asian & African Voices
We cover Chinese, Japanese, Korean, Malay, Swahili, and Arabic. These languages allow you to reach diverse user bases with clear, natural-sounding audio that fits modern app standards.
bullets
Simple Integration
Integrate Narrivo’s TTS API into your startup’s stack with zero friction. Our endpoint mirrors the OpenAI speech interface, allowing you to swap providers without rewriting your core logic. Simply point your client to our base URL and use standard request bodies.
OpenAI Compatible
The API follows the same request shape as the OpenAI speech endpoint. You send a JSON payload with fields like model, input, voice, and response_format. This compatibility means you can use existing integrations with minimal code changes.
Quick Curl Example
You can start generating speech immediately using a simple command. The following request sends text to the API and saves the audio file locally.
- curl -X POST https://api.playbd4.com/v1/audio/speech \
- -H "Authorization: Bearer YOUR_API_KEY" \
- -H "Content-Type: application/json" \
- --data '{"model": "tts-1", "input": "Hello, this is a test.", "voice": "nova", "response_format": "mp3"}' \
- -o output.mp3
SDK Support
Leverage official OpenAI SDKs by adjusting the base URL. No need for a custom library or waiting for an SDK release. Just update the client configuration to point to https://api.playbd4.com/v1 and use the standard speech method.
Transparent Pricing
Narrivo charges $0.01 per 1,000 characters, making it easy to predict costs for your app’s notifications or UI text. Failed requests are free, so you only pay for successful synthesis. This pay-per-character model scales with your usage, with no monthly plans or minimum spend required.
Pay Per Character
Each request processes up to 4,096 characters. Spaces and punctuation count toward the total. You can split longer texts into parts and join the audio files manually.
No Hidden Fees
There are no subscriptions, seats, or VAT invoices. Balance does not expire. Top-ups are made via USDT on TRON (TRC-20), credited automatically within minutes.
Free Trial Credit
Sign in with Google to receive $0.50 in free credit, valid for 7 days. This covers approximately 50,000 characters, allowing you to test all voices and formats before committing.

Technical Reliability
Reliable delivery matters for user-facing audio. Short phrases take a few seconds to synthesize, while longer texts generate at approximately real-time speed (25 characters per second). If the system is busy, requests are queued to maintain stability without losing data.
This predictable cadence helps you plan latency expectations for your app’s notifications or interface elements without needing complex buffering logic.
High Speed Generation
Generation Speed Short phrases take a few seconds to synthesize. Longer texts generate at approximately real-time speed (25 characters per second). Requests are queued if the system is busy.
Multiple Formats
Choose between mp3, wav, opus, flac, or pcm. Selecting the right format balances file size and quality for your specific use case, whether it’s a quick mobile notification or a high-fidelity in-app feature.
All formats are delivered directly in the API response, ready to be played or stored immediately.
- mp3 for universal compatibility
- wav for high-quality local playback
- opus for efficient bandwidth usage
Standard Limits
Each request supports up to 4096 characters. For longer texts, split the input into parts and join the resulting audio files. You can adjust the speed between 0.25x and 4.0x to fit your content’s pacing.
The API allows 60 requests per minute per key, ensuring consistent performance during peak usage.
Data Privacy First
Your input text is used solely to generate the requested audio file and is never used for training our models. We respect the privacy of your app’s users by keeping their data isolated to the immediate generation process.
Generated audio is returned directly in the response and is not stored on our servers. We retain only request metadata—such as timestamp, character count, and status—strictly for billing purposes, ensuring transparency without compromising user data.
No Training Data
Unlike some competitors, we do not use your input text to improve our voice engines. Your content remains yours, used only for the specific audio synthesis request you submit.
No Storage
The audio files generated for your API calls are delivered immediately and not kept on our infrastructure. We do not archive the audio content of your users' interactions.
Request metadata (time, characters, status) is kept for billing verification. This minimal data allows us to process your usage accurately without retaining the actual speech content.
Secure Keys
Each account uses a single active API key. If you suspect any compromise, you can issue a new key at any time, and the old one stops working instantly.
Keys are sent via the standard Authorization: Bearer header, compatible with your existing secure infrastructure.
Get Started Today
Getting your voice into your app is straightforward. Create an account using your Google login or email to access your dedicated dashboard. There are no subscriptions or credit cards required to start.
Once signed in, your unique API key is generated instantly. This key authenticates your requests to the speech endpoint, allowing you to begin testing immediately without waiting for approval.
Sign Up with Google
Use your existing Google account to create a Narrivo account in seconds. This method triggers a free trial credit of $0.50, valid for 7 days, giving you about 50,000 characters to test the service risk-free.
- Instant account creation
- Free trial credit included
- No credit card required
Get Your API Key
Navigate to the dashboard to view your active API key. Copy this key to use in your Authorization header. If needed, you can issue a new key at any time, which invalidates the old one immediately.
First Request in Minutes
Send a simple POST request with your text and chosen voice. The API returns an audio file in your preferred format. With typical speeds of roughly 25 characters per second, you will hear results quickly for short phrases.
Common Questions
This section answers frequent questions about integrating Narrivo into your startup’s voice workflows. We focus on clear, practical details so you can decide quickly if our API fits your product.
All answers are based on current API behavior. Features and limits may change, so check the documentation for the latest specifications.
Voice Selection
We offer eight distinct presets designed for specific use cases. Choose warm narrators like Aria for stories, or energetic voices like Felix for promos. Each voice supports all 23 languages, so you can maintain consistency across regions.
- 8 curated voice presets
- All voices support all 23 languages
- Adjustable speed from 0.25x to 4.0x
Language Support
The API supports 23 languages, including English, Hindi, German, Spanish, and Japanese. Any voice can speak any supported language. If you do not set the language, the system guesses it from the text script.
- 23 supported languages
- Automatic language detection for Latin script
- Explicit language code recommended for non-English text
Pricing Model
You pay $0.01 per 1,000 characters. Spaces and punctuation count toward the limit. Failed requests are free, and you only pay for successful synthesis. There are no monthly plans or hidden fees.
- $10 per 1 million characters
- $0.50 free trial credit for new Google sign-ups
- Pay only for successful requests
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
- OpenAI API reference: create speech
- LibriTTS-R paper (arXiv 2305.18802)
- Python documentation
- openai-python on GitHub
- LibriVox public-domain audiobooks
- ISO 639 language codes
- FFmpeg documentation
- W3C WAI: making audio and video accessible
- Node.js documentation
- LibriTTS-R corpus (OpenSLR 141)
- Creative Commons Attribution 4.0
