Frequently asked questions
Who runs NavVoice?
NavVoice is an independent storefront for a cloud text-to-speech API. We are not affiliated with OpenAI, Google, Amazon, or any other major brand. Our team focuses on providing a reliable API endpoint for automotive teams to generate high-quality audio for in-car navigation systems at scale.
Are the voices licensed?
Yes. Every generated file carries an inaudible watermark marking it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures clear licensing for the underlying voice data used in your navigation audio generation.
Is my text used for training?
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 like time, characters, and status solely for billing purposes, ensuring your navigation data remains private and secure.
Do you store generated audio?
No. Generated audio is returned in the response and not stored. Only request metadata, including time, characters, and status, is kept for billing purposes. This ensures that your navigation audio files are transient and not retained on our servers after delivery to your application or device.
How can I contact support?
Support is available by email only. We do not offer a phone number, live chat, or physical address. For any issues regarding your NavVoice API integration, billing, or technical questions, please reach out via email. We aim to assist automotive teams with specific, factual support through this channel.
Is this an official OpenAI product?
No. NavVoice is not affiliated with OpenAI. We use a similar request shape to the OpenAI speech endpoint, so their SDKs work by changing the base URL. However, we are an independent storefront. We do not claim to be the official product of OpenAI or any other brand.
What is the CC BY 4.0 license?
CC BY 4.0 is a Creative Commons Attribution license. Our voices are based on recordings from LibriTTS-R, which is licensed under CC BY 4.0. This means the underlying voice data can be used with proper attribution. It ensures that the audio generated for your car navigation systems has clear, permissive licensing origins.
Do you offer refunds for failed requests?
Yes. If synthesis fails, the charge is returned in full. You pay $10 per 1 million characters, but you only pay for successful generations. This ensures that your team is not charged for audio that did not complete, maintaining fairness for high-volume automotive navigation audio generation workflows.
Can I use this API for commercial projects?
Yes. NavVoice is designed for large automotive teams to generate high-quality TTS audio for in-car navigation and infotainment systems. There are no monthly plans or seats, just pay-as-you-go pricing. You can use the generated audio for commercial purposes, provided you adhere to the licensing of the underlying voice data.
Is there a phone number for support?
No. Support is by email only. We do not offer a phone number, live chat, or physical address. For any questions about the NavVoice API, billing, or technical issues, please contact us via email. This keeps our support process simple and focused on written, traceable communication for your team.
Do you have a physical address?
No. NavVoice is a cloud-based API service. We do not have a physical address or on-premise install option. Our infrastructure is hosted in the cloud, allowing automotive teams to integrate our text-to-speech capabilities directly into their navigation systems without needing to manage physical hardware or local servers.
Are you affiliated with Google or Amazon?
No. NavVoice is an independent storefront. We are not affiliated with Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We use a similar API structure to OpenAI, but we are a separate entity. Our focus is solely on providing a reliable TTS API for automotive teams.
Who We Are
NavVoice is an independent storefront for a cloud text-to-speech API focused on delivering high-quality text-to-speech audio for automotive navigation systems. We specialize in generating crisp, clear voiceovers for in-car infotainment, ensuring drivers receive accurate instructions without distraction.
Our team understands the unique acoustic challenges of vehicle cabins, optimizing voice outputs for clarity and consistency across diverse driving environments.
Independent Editorial Team
We operate independently, free from the constraints of larger tech giants. Our API provides eight voice presets suitable for navigation cues.
Focus on Navigation Audio
Our API is designed to handle the specific pacing and tone required for turn-by-turn directions. We prioritize clarity in languages like Hindi, Arabic, and English, ensuring critical information is never lost in noise.
- Optimized for short navigation commands
- Clear enunciation for critical instructions
- Support for 23 languages including Hindi and Arabic
Large Team Solutions
Designed for large automotive teams, our API scales with your production needs. With a rate limit of 60 requests per minute per key, you can generate thousands of navigation segments efficiently.
Our API Technology
NavVoice delivers a cloud-based text-to-speech API designed for automotive teams generating navigation audio at scale. The endpoint accepts standard JSON payloads, allowing you to integrate directly using official OpenAI SDKs by simply adjusting the base URL to our domain.
This architecture ensures seamless compatibility with existing development workflows. Teams can generate high-quality audio files for in-car systems without adopting a proprietary protocol, ensuring consistent performance across Hindi, English, and 21 other languages.
OpenAI-Compatible
Our API mirrors the request shape of the OpenAI speech endpoint. By changing the base_url to https://api.play3666.com/v1 and using your unique key, you can use standard libraries to send text and receive audio files instantly.
The endpoint supports POST requests with fields for model, input, voice, response_format, speed, and optional language. This familiarity reduces integration time for engineering teams building infotainment systems.
- Endpoint: POST /v1/audio/speech
- SDKs: Official OpenAI SDKs work with base_url change
- Auth: Bearer token with single active key
8 Voice Presets
Select from eight distinct voice presets optimized for clarity in vehicle cabins. Options include female voices like Aria and Luna, and male voices like Felix and Orion, each tailored for specific tones from energetic promos to calm navigation instructions.
These voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Every generated file includes an inaudible watermark to identify it as synthetic speech, ensuring transparency for your users.
- Female: Aria, Nova, Luna, Sage
- Male: Felix, Milo, Atlas, Orion
- Source: Licensed LibriTTS-R and LibriVox
23 Languages Supported
NavVoice supports 23 languages, including Hindi, Arabic, English, and others critical for global automotive markets. Any voice can speak any of these languages, allowing you to maintain consistent voice quality across multilingual routes.
If the language field is unset, the system guesses from the script, defaulting to English for Latin text. For non-English Latin-script text, explicitly set the language code to ensure accurate pronunciation.
- Includes: Hindi, Arabic, English, French, German, Japanese, Korean
- Not supported: Vietnamese, Indonesian, Thai
- Default language detection for Latin scripts

Voice Licensing
NavVoice’s eight voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), which uses readings from LibriVox public-domain audiobooks. This foundation provides the voice data used by the NavVoice API.
LibriTTS-R Source
We use the LibriTTS-R dataset, which contains clean speech from public-domain audiobooks. This provides a robust, diverse base for our TTS engine, ensuring clear audio for drivers.
CC BY 4.0 License
The underlying recordings are licensed under CC BY 4.0. This allows us to build and distribute synthetic voices legally while maintaining transparency about our data sources for automotive teams.
Public Domain Readings
All source audio comes from LibriVox, where volunteers read public-domain books. This means the original performances are free of complex copyright restrictions, simplifying licensing for large-scale navigation deployments.
Data Privacy Policy
NavVoice processes your input text exclusively to generate the required audio file. We do not use your navigation scripts or voiceover data to train our underlying models, ensuring your proprietary route instructions remain yours alone.
Generated audio is delivered directly in the API response and is not stored on our servers after delivery. This transient handling minimizes data exposure.
No Training Data
Your text inputs are used solely for synthesis. We do not consume your navigation audio or scripts for model improvement, keeping your creative assets distinct from our engine’s development.
This separation ensures that your specific voiceover choices for routes in Hindi, English, or Arabic do not influence future model outputs, preserving the integrity of your brand’s audio identity.
- Input text used only for immediate synthesis
- No consumption for model training
No Audio Storage
Once the audio file is returned to your request, it is not persisted in our storage systems. This reduces the risk of long-term data retention issues for large automotive teams processing thousands of daily routes.
If you need to keep the audio, you are responsible for storing it in your own infrastructure immediately after the API call returns.
Billing Metadata Only
We retain minimal metadata—timestamp, character count, and status—strictly for billing accuracy and request tracking. This data does not include the actual text or audio content.
This limited retention supports transparent usage reporting.
- Timestamp, character count, and status kept
- No text or audio content retained

Honest Limitations
NavVoice is designed for batch generation and standard playback, not real-time streaming. Audio is returned as a complete file after synthesis completes. This means you cannot receive partial audio chunks during generation, which suits most navigation route updates but differs from live conversational agents.
We do not support SSML markup for fine-grained control over pronunciation or pauses. You control pacing primarily through the speed parameter (0.25–4.0) and by splitting text into smaller segments. This simplifies integration but removes granular audio editing capabilities.
No Streaming Audio
Requests are processed sequentially, and the full audio file is returned upon completion. There is no WebSocket or chunked transfer for partial audio. This ensures consistent billing and simpler error handling for large navigation text batches.
No SSML Support
The API accepts plain text inputs. There is no SSML (Speech Synthesis Markup Language) support for adjusting pitch, rate, or phonetic pronunciation per word. Speed adjustments apply globally to the entire request input.
No Custom Cloning
We offer eight preset voices derived from licensed recordings, but we do not offer custom voice cloning. You cannot upload a sample to create a unique brand voice. All generated files include an inaudible watermark marking them as synthetic speech.
No emotion tags or custom pronunciation lexicons are available. Voice selection is limited to the eight provided presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion.

Contact Us
NavVoice provides support by email for automotive teams generating navigation audio at scale. Our channel is designed to handle technical inquiries regarding API limits, voice selection, and billing for multilingual TTS workflows.
Email Support Only
We communicate exclusively via email. There is no phone number to call for urgent issues, and we do not maintain a direct line for sales or engineering queries. Send your request to [email protected].
No Live Chat
Unlike many consumer apps, we do not offer live chat widgets on this site. This allows our team to focus on resolving complex integration questions without the distraction of simultaneous chats.
Response Time
We aim to reply to all emails within 24 hours during business days. During high-volume periods, such as major navigation software updates, response times may vary slightly. Please include your API key in the subject line for faster tracking.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Our navigation system ensures precise routing for every vehicle in the fleet.
23 languages
Any voice speaks any of these languages.
