Frequently asked questions
Who owns the voices?
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 recordings, but we provide the synthesis engine and infrastructure to generate the audio files for your projects.
Are the voices synthetic or recorded?
The output is synthetic speech generated from licensed source recordings. Every generated audio file carries an inaudible watermark that marks it as synthetic speech, distinguishing it from direct recordings while maintaining high fidelity based on the original voice performances.
Do you sell user data?
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 (time, characters, status) strictly for billing purposes.
Is there a phone number for support?
No. We do not offer a phone number or live chat. All support inquiries are handled via email only. This allows us to maintain a lean, engineering-focused operation without the overhead of call centers or extended support hours.
Do you have an SLA?
No. We do not provide an SLA, uptime guarantee, or enterprise contract. Requests are processed sequentially, so under load a request may wait in a queue. We aim for reliability but do not guarantee specific availability metrics.
Are you affiliated with OpenAI?
No. We are not affiliated with OpenAI, despite our API endpoint and request shape being compatible with the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to our API domain.
Can I use the voices for commercial projects?
Yes. The source recordings are licensed under CC BY 4.0 or are public domain. You can use the generated audio for commercial advertising, radio spots, and other projects. The generated files are yours to use upon successful synthesis.
Is the API open source?
No. We do not offer an official SDK of our own, nor is the underlying synthesis engine open source. You interact with the API via standard HTTP requests or compatible SDKs like the OpenAI Python/Node libraries.
Do you store my API key?
We store your active API key on our servers to authenticate your requests and track usage against your balance. You can issue a new key at any time, and the old one stops immediately, ensuring you control access.
What is your email address?
Support is available by email only. We do not have a phone number or live chat option for customer support.
Do you have a GDPR certificate?
No. We do not have a GDPR certificate, SOC 2 certification, or HIPAA compliance. We are an independent storefront without enterprise contracts or formal certifications. We process data strictly for synthesis and billing as described in our privacy facts.
Is the API SOC 2 compliant?
No. We do not hold SOC 2 certification or any other security certifications. We are a small, independent API provider. We manage data securely but do not undergo third-party audits to maintain formal compliance certificates.
Can I get a custom voice?
No. We do not offer custom voice cloning, voice design, or uploading your own voice. You choose from our 8 preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) which are based on licensed source recordings.
Do you offer refunds?
Failed requests are free: if synthesis fails, the charge is returned in full. For successful requests, we do not offer refunds. Top-ups via USDT on the TRON network (TRC-20) are credited automatically and do not expire. There are no monthly plans to cancel.
Who We Are
SpotVoce is an independent text-to-speech API provider built specifically for advertising agencies and radio production teams. We offer a standardized TTS endpoint that integrates directly into your creative workflows, eliminating manual hand-offs and ensuring consistent, programmable voice-over for video and audio spots.
Our engineering focus prioritizes reliability and speed. The API processes requests sequentially, delivering audio files that match real-time speech rates for long texts, while short phrases generate in a few seconds. Under load, a request may wait in a queue.
Independent API Provider
Unlike platform-dependent solutions, SpotVoce operates as a standalone infrastructure. This independence ensures that our service remains distinct and directly accountable to our agency clients, with clear billing and usage metrics.
Engineering Focus
We engineer for precision. The API accepts standard JSON bodies compatible with OpenAI SDKs, allowing you to swap the base URL and continue using existing code. Rate limits are set at 60 requests per minute, ensuring stable throughput for batch production without unpredictable spikes.
Agency-First Design
Our system is designed for high-volume creative output. You can split long scripts into 4096-character chunks and join the resulting audio files seamlessly. This approach lets you maintain full control over pacing and editing, integrating TTS into your existing post-production pipelines without disrupting your workflow.
Voice Licensing
SpotVoce’s voice presets are built on licensed recordings from the LibriTTS-R dataset, providing a standardized audio foundation for our eight distinct voice models. This source ensures consistent acoustic quality across all generated audio files.
LibriTTS-R Source
We utilize the LibriTTS-R dataset as the primary source for our voice synthesis engines. This dataset contains speech recordings that form the basis of our eight voice presets.
CC BY 4.0 License
The underlying recordings are licensed under Creative Commons Attribution 4.0 (CC BY 4.0). This license allows us to use, modify, and distribute the audio data for commercial purposes, including your advertising and radio spot productions, without additional royalty fees.
Public Domain Readings
Many of the base recordings originate from LibriVox, featuring public-domain audiobook readings. This dual-layer licensing structure provides legal clarity for agencies integrating SpotVoce into their commercial workflows, combining open-source accessibility with reliable commercial usage rights.
Data Policy
SpotVoce processes input text strictly to generate the requested audio file. We do not use your raw text for training our models or improving voice synthesis algorithms. The text is processed in real-time and discarded once the audio is returned in the response.
Generated audio files are returned in the API response and are not stored on our servers after delivery. This ensures that your creative assets remain under your control immediately upon generation.
Input Text Usage
Input text is used exclusively for the purpose of synthesis. Once the audio file is generated and delivered, the original text string is not retained for model training or secondary analysis. This ensures that your script content remains private and is not ingested into our training datasets.
Audio Storage Policy
We do not store the generated audio files after they are returned in the API response. Your audio assets are generated on-demand and are yours to download and store locally or in your own cloud storage immediately. This minimizes our storage footprint and ensures no lingering copies exist on our servers.
Metadata Retention
Request metadata, including timestamp, character count, voice used, and status, is retained for billing and usage verification purposes. This data is kept only as long as necessary to support your account balance and usage history.
Technical Infrastructure
SpotVoce runs on a standard cloud infrastructure designed for high-throughput API requests. We do not offer on-premise installations or data-center selection options. All processing occurs in a single geographic region.
Cloud-Based Architecture
Our service is entirely cloud-based, relying on scalable compute resources to handle request queues. Requests are processed sequentially, so peak loads may introduce slight delays during synthesis.
No On-Premise Option
We do not provide on-premise deployment or private cloud instances. There is no option to install the engine within your own data center or virtual private cloud.
Single Region Deployment
All audio generation happens in one region. We do not offer multi-region redundancy or specific data-center choices, so all requests originate from the same physical location.

Support Model
SpotVoce maintains a lean operational model to keep API costs low for advertising agencies. Support is handled exclusively via email, ensuring every inquiry is tracked, documented, and resolved by technical staff familiar with TTS integration workflows.
This approach avoids the overhead of call centers and live chat queues, allowing us to direct resources toward API reliability and pricing transparency rather than real-time support tiers.
Email Only
All support requests are managed through a single email channel. This ensures that technical details, such as curl examples or error logs, are preserved for reference and resolution.
No Live Chat
We do not offer real-time live chat widgets on our website. This eliminates the need for large support teams and keeps our operational costs stable, which helps maintain our competitive per-character pricing.
No Phone Support
There is no dedicated phone number for SpotVoce support. Phone support is often inefficient for technical API issues where code snippets and logs are more effective. Email allows for asynchronous, precise communication suited for engineering teams.
Not Affiliated With
SpotVoce is an independent entity, not a subsidiary or partner of any major voice technology provider. Our API, SDK compatibility, and voice models are developed and maintained separately.
OpenAI
We use the same JSON request shape as the OpenAI speech endpoint, which allows you to point your existing OpenAI SDK to our base URL. However, we are not affiliated with OpenAI. Our models, voices, pricing, and infrastructure are entirely distinct.
ElevenLabs
While both services provide high-quality text-to-speech APIs, SpotVoce operates independently. We do not use ElevenLabs voices, nor do they use ours. Our voice presets are based on licensed LibriTTS-R recordings, whereas ElevenLabs uses its own proprietary models.
Other Major Brands
We are not affiliated with Google, Amazon, Microsoft, or any other major cloud or AI brand. Our infrastructure is self-managed, and our voice library is distinct from theirs.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Her gentle tone reduces listener fatigue during longer audio spots.
23 languages
Any voice speaks any of these languages.
