Frequently asked questions
Are you affiliated with OpenAI?
No, VoiceSwitch is not affiliated with OpenAI. We are an independent storefront for a distinct text-to-speech API. While our endpoint structure and SDK compatibility mimic the OpenAI speech endpoint for convenience, our engine, voices, and infrastructure are separate. We do not use OpenAI’s models or servers.
Who owns the voice recordings?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We provide these as presets. The underlying source material is public domain or licensed, but the specific synthetic audio files generated by our API are produced by our infrastructure.
Can I use the audio commercially?
Yes. The source recordings are from LibriVox (public domain) or licensed under CC BY 4.0. Since we generate synthetic audio using these sources, you can use the resulting files commercially. Each generated file carries an inaudible watermark marking it as synthetic speech, but this does not restrict your usage rights.
How do I contact support?
Support is available by email only. We do not offer a phone number, live chat, or a community forum. You can reach us via the contact page or by emailing the support address provided in your account dashboard.
Do you store my input 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 not stored. We keep request metadata (time, characters, status) solely for billing purposes. Your actual text content is not retained after generation.
Is the API open source?
No, our API is not open source. We provide a proprietary cloud text-to-speech API. You interact with it via standard HTTP requests or compatible SDKs, but the underlying engine and infrastructure are closed. We do not offer an official SDK of our own, only compatibility with existing tools.
Can I request a specific voice?
You can choose from our 8 preset voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. You cannot request custom voice cloning or upload your own voice. Each voice is a distinct preset designed for specific tones, such as warm narration or energetic promos, but the selection is fixed.
Do you offer refunds?
Failed requests are free; if synthesis fails, the charge is returned in full. We do not offer automatic refunds for completed generations, but we ensure you only pay for successful audio outputs.
What is your uptime policy?
We do not offer an SLA or an uptime guarantee. Our service is provided on a best-effort basis. Requests are processed sequentially, so under load, a request may wait in a queue. We do not provide enterprise contracts or specific uptime metrics, so plan accordingly for production workloads.
Do you have a privacy policy?
Yes, we respect your privacy. Input text is used only for generation and not for training. Generated audio is not stored. We retain request metadata for billing.
Can I use my own voice?
No, we do not offer custom voice cloning for customers. You cannot upload your own voice or design a custom voice. You must choose from our 8 preset voices. If you need your specific voice, you would need to generate audio using our presets or use a different service.
Is there a community forum?
No, we do not have a community forum. Support is provided exclusively via email. There is no live chat, phone number, or social community space for users. All communication regarding your account, billing, or technical questions should be directed to our support email address.
Do you accept other cryptocurrencies?
No, we accept USDT on the TRON network (TRC-20) only. We do not accept Bitcoin, Ethereum, or other cryptocurrencies. We also do not accept credit cards, PayPal, or subscriptions. Top-ups are credited automatically within minutes after the transfer is confirmed on the blockchain.
Who are your competitors?
We are an independent alternative to providers like Amazon Polly, Natural Reader, ElevenLabs, and Google Cloud TTS. Our API offers a similar request shape to OpenAI but uses our own engine and voice presets, often at a lower cost.
Who We Are
VoiceSwitch is an independent editorial team that builds and maintains a dedicated storefront for a cloud text-to-speech API. We focus on delivering clear, practical documentation and transparent pricing so creators can integrate professional voiceovers without navigating complex enterprise contracts or hidden fees.
Independent editorial team
We provide technical details and pricing structures for the API, ensuring that every guide and code example reflects current capabilities. We do not manage the underlying voice synthesis engines; we simply provide the interface and documentation needed to use them effectively.
Focused on YouTube creators
We design our workflow examples specifically for YouTubers and freelance content producers who need reliable, cost-effective voiceovers. Our documentation highlights how to handle character limits, manage audio formats like MP3 and WAV, and integrate with standard editing pipelines without requiring specialized audio engineering knowledge.
- Step-by-step integration guides for video production
- Optimized for long-form narration and short clips
- Clear character counting to manage budget
No affiliation with major brands
VoiceSwitch operates independently and is not affiliated with OpenAI, Amazon, Google, or any other major technology brand. We are a distinct storefront for the VoiceSwitch API, offering a neutral comparison point for creators migrating from legacy providers like Amazon Polly or Natural Reader.
Our Voice Licensing
Our voice presets are built on licensed recordings from the LibriTTS-R dataset. These voices are derived from audiobook readings available on LibriVox, ensuring a natural and consistent sound for your YouTube content and freelance projects.
LibriTTS-R recordings
The eight available voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) are based on licensed recordings from the LibriTTS-R dataset. This dataset provides the foundation for clear, professional narration suitable for long-form videos and short clips alike.
CC BY 4.0 licensed
The underlying audio data is licensed under CC BY 4.0. This allows for flexible use in commercial and non-commercial projects without complex royalty structures. You can integrate these voices into your workflow without worrying about restrictive licensing terms.
LibriVox public domain sources
Source materials originate from LibriVox, a platform hosting public domain audiobooks. By leveraging these public domain readings, we ensure that the core voice models are built on legally sound, openly accessible content. This transparency supports our goal of providing a reliable, independent API for creators.
- Based on public domain audiobooks
- CC BY 4.0 license
- Transparent source data
Data Privacy Policy
When you send text to our API, it is processed solely to generate the requested audio file. We do not use your input data to train our models or improve the engine, ensuring your content remains yours.
Text not used for training
Your input text is used exclusively for the immediate production of audio. It is not ingested into our training datasets, so your unique scripts or creative works are not used to refine the voice models used by other customers.
Audio not stored permanently
Generated audio is returned directly in the response and is not permanently stored on our servers. Generated audio is returned in the response and not stored.
Metadata kept for billing
We retain request metadata—including timestamp, character count, and status—for billing accuracy. This ensures you are charged correctly for your usage without retaining the actual content of your voiceovers for extended periods.
Technical Limits
VoiceSwitch is a straightforward API designed for efficiency and cost control. While we deliver high-quality audio, our architecture prioritizes stability over real-time interactivity. Understanding these boundaries helps you integrate our voices into your YouTube workflow without unexpected surprises.
No streaming audio
We return complete audio files via the API response. There is no WebSocket or streaming endpoint for partial audio chunks. You must wait for the full synthesis to complete before playing the result.
No SSML support
Our API accepts plain text input. We do not support Speech Synthesis Markup Language (SSML). You control pacing by adjusting the speed parameter or by splitting text manually.
No custom voice cloning
We offer eight fixed presets based on licensed recordings. We do not provide custom voice cloning or allow you to upload your own audio samples to create a unique voice. Each generated file carries an inaudible synthetic watermark.

How We Operate
VoiceSwitch operates as a lean, independent storefront for the VoiceSwitch TTS API. We prioritize transparency and simplicity in how we handle payments and support, ensuring you know exactly how the service works without hidden layers or corporate bureaucracy.
USDT payments only
We accept USDT on the TRON network (TRC-20) exclusively for top-ups. There are no credit cards, PayPal options, or monthly subscriptions to manage. Minimum deposits are $5, and credits appear in your balance automatically within minutes of transfer.
- USDT (TRC-20) only
- No credit cards or PayPal
- No monthly subscriptions
- Minimum $5 top-up
- Automatic credit within minutes
Email support only
All inquiries are handled via email. We do not offer phone support or live chat, keeping our operations straightforward and cost-effective.
- Email support only
- No phone support
- No live chat
No phone or live chat
Unlike larger providers, we do not maintain 24/7 call centers or instant chat widgets. If you need assistance, you will receive a detailed email response. This model ensures we remain an independent, efficient alternative for your TTS needs.
Contact Us
VoiceSwitch is an independent storefront operated by a small editorial team dedicated to YouTube creators. We are not affiliated with OpenAI, Amazon, or any other major brand mentioned in comparisons. Our operations are transparent, and we handle all inquiries through a single, reliable channel.
Email only for support
We do not offer a phone number, live chat, or in-app messaging. All support requests go to our email address. This keeps our team focused and ensures every question receives a thoughtful reply without the noise of multiple channels.
No SLA guarantees
We do not guarantee specific uptime percentages. As a lean operation, we prioritize consistent API performance over contractual SLAs. You can expect reliable service, but we do not offer enterprise contracts or formal uptime guarantees.
Transparent operations
We keep request metadata for billing purposes but do not store generated audio permanently. Your input text is used only for synthesis and never for training. We clearly state what we do and do not offer, so you know exactly what you are buying.
Pricing and Payments
VoiceSwitch offers straightforward, usage-based pricing for YouTube creators and freelancers. You pay only for what you generate, with no hidden fees or monthly commitments.
Our rates are transparent and competitive, making it easy to budget for your voiceover projects without worrying about sudden cost increases.
$0.01 per 1,000 characters
The cost is $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward the total character count. Failed requests are free, ensuring you only pay for successful audio generation.
USDT (TRC-20) top-ups only
We accept USDT on the TRON network (TRC-20) for top-ups. The minimum amount is $5, and credits are automatically added to your balance within minutes of transfer. We do not support credit cards, PayPal, or invoices with VAT.
Free trial credit available
New accounts created via Google sign-in receive $0.50 in free trial credit, valid for 7 days. This allows you to test the API with approximately 50,000 characters of text before committing to a top-up.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Consistent uploads build trust with your viewers and steadily grow your subscriber base over time.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- TRON developer hub: TRC-20
- Tether (USDT)
- Creative Commons Attribution 4.0
- W3C WAI: making audio and video accessible
- LibriVox public-domain audiobooks
- openai-node on GitHub
- OpenAI API reference: create speech
- ISO 639 language codes
- LibriTTS-R paper (arXiv 2305.18802)
- FFmpeg documentation
- LibriTTS-R corpus (OpenSLR 141)
