About the VerbaSync Editorial Team and API

By VerbaSync editorial team · Updated 2026-11-19

This page explains how the VerbaSync API is built, licensed, and operated for localization and dubbing agencies. You will find clear details on the public-domain sources for our voices, and exactly how your data is handled during synthesis.

If you are managing large translation teams, this section clarifies our technical limits, data retention policies, and support structure. We aim to provide transparent facts about the API so you can integrate it confidently into your dubbing pipelines without hidden overhead.

About the VerbaSync Editorial Team and API

Frequently asked questions

Who runs this site?

VerbaSync is an independent storefront for a text-to-speech API. We operate this specific instance at ux45.info, providing access to the same core engine used by our network. We focus on delivering consistent, licensable synthetic voices optimized for professional dubbing pipelines without the overhead of managing voice talent.

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 matches the OpenAI speech endpoint for compatibility, but we use our own infrastructure and keys. We are a distinct entity providing an alternative solution for TTS needs.

Where do the voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), which originates from LibriVox public-domain audiobook readings. These sources provide the base audio data for our synthetic voices, including Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion, ensuring a solid foundation for high-quality speech generation.

Is the data private?

Yes. Your 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 respect your privacy by ensuring that the content you send for synthesis remains dedicated solely to that specific generation task.

Do you store my text?

No. Input text is used only to produce the audio and is not stored after generation. We do not retain the actual text content you send to our API. Only request metadata, such as time, characters, and status, is kept for billing and usage tracking purposes.

How long is metadata kept?

Request metadata, including time, characters, and status, is kept for billing purposes. We retain this data to accurately track your usage and ensure correct charging based on the character count.

Is there a physical office?

We do not maintain a physical office or on-premise install option. Our service is entirely cloud-based, accessible via our API endpoints. We operate as a distributed team, allowing us to focus resources on delivering reliable text-to-speech synthesis without the overhead of physical infrastructure or data-center choices.

Can I talk to a human?

We do not offer phone support or live chat. All support is handled via email. If you have questions or need assistance, please reach out through our contact page. We aim to respond to your inquiries promptly, but you will communicate with our support team via email only.

Is the license commercial?

Yes. The voices are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings. You can use the generated audio for commercial projects like dubbing. However, we do not provide legal advice, so please verify specific license terms for your intended use case.

Do you offer refunds?

Failed requests are free, and the charge is returned in full if synthesis fails. We do not offer refunds for successful requests. If you are unsatisfied with the quality of a successfully generated audio file, the charge stands. Your balance does not expire, allowing you to use credits anytime.

Are voices copyrighted?

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. While the source material has specific licenses, the synthetic voices themselves are generated by our engine. We do not claim copyright on the synthetic output, but the underlying data sources have their own terms.

Is the site secure?

We do not provide specific certifications like SOC 2, HIPAA, or GDPR certificates. We do not guarantee uptime or offer an SLA. You can use our API securely, but we recommend verifying our security posture through our documentation and contact.

Can I suggest a voice?

We do not offer custom voice cloning or voice design. You cannot upload your own voice or suggest new voices for the current set of eight presets. Our voices are fixed presets based on existing licensed recordings. If you need a specific voice, you must choose from the available options.

How do I contact support?

Support is available by email only. There is no phone number or live chat. You can reach us through the contact page on our site. We do not offer 24/7 support, so please allow time for our team to review and respond to your email inquiries regarding your account or API.

Who We Are

Sound wave illustration for: Who We Are

VerbaSync is an independent storefront for a text-to-speech API, designed to serve localization and dubbing agencies with consistent, high-quality synthetic voices. We help teams synthesize audio from scripts without the overhead of managing voice talent for every language, delivering licensable voices optimized for professional dubbing pipelines.

Editorial Team Background

Editorial Team Background

We are a small, focused team with deep roots in editorial and localization workflows. Our background ensures that the voices we provide are clear, natural, and suitable for professional narration, whether for audiobooks, instructional content, or broadcast.

Focus on Localization

Focus on Localization

We support 23 languages, allowing agencies to maintain consistent voice identity across diverse markets. Our API integrates directly into your dubbing pipeline, enabling rapid production of audio files from text inputs without the logistical burden of coordinating multiple voice actors.

Independent Storefront

Independent Storefront

As an independent storefront, we operate separately from major tech brands. We provide direct access to the API, transparent pricing, and dedicated support via email, ensuring you have full control over your audio production process without hidden dependencies or branding confusion.

Voice Licensing

Sound wave illustration for: Voice Licensing

We synthesize voices using the LibriTTS-R dataset, sourced from LibriVox audiobook readings. This foundation provides synthetic speech based on licensed recordings.

LibriTTS-R Dataset

LibriTTS-R Dataset

Our eight voice presets—aria, nova, luna, sage, felix, milo, atlas, and orion—are based on licensed recordings from the LibriTTS-R dataset. These voices provide the consistent tone and quality required for localization agencies handling large-scale script translations.

CC BY 4.0 License

The underlying dataset is based on recordings licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). This allows us to deliver high-quality audio while maintaining clear licensing terms for your dubbing projects, ensuring your generated content remains usable for commercial distribution.

Public Domain Sources

All voice data originates from LibriVox public-domain audiobook readings. By leveraging these established recordings, we provide a stable, reliable voice engine that scales with your team’s needs, free from the variability of live studio sessions or complex talent contracts.

Data Policy

Sound wave illustration for: Data Policy

We prioritize clarity for localization agencies managing sensitive scripts. Our policy ensures that your input text is used solely to produce the requested audio file and is never utilized for training our underlying models.

Input Text Usage

When you send text to the API, it is processed only for the immediate generation of the audio file. Once synthesized, the text is not retained for model improvement or reused in other contexts.

Audio Storage

Generated audio files are returned directly in the API response and are not stored on our servers. This means you retain full control over your audio assets without us holding copies for extended periods.

Metadata Retention

We keep request metadata, including timestamp, character count, and status, strictly for billing and usage verification. This data helps us ensure accurate charges and troubleshoot issues without storing the actual content of your scripts.

Technical Limits

Sound wave illustration for: Technical Limits

VerbaSync is a pure API. We deliver complete audio files via standard HTTP responses, so you control the buffering and playback logic in your own pipeline. We do not offer WebSocket streaming, SSML markup, or phoneme-level pronunciation control, keeping the integration simple and predictable for automated dubbing workflows.

Our voices are static presets derived from the LibriTTS-R dataset, so we do not offer custom voice cloning or custom voice design. You select from eight licensed presets that speak all 23 supported languages, ensuring consistent quality across your entire project without managing individual talent contracts.

No Streaming

We return fully synthesized audio files (mp3, wav, opus, flac, pcm) rather than streaming partial chunks. This design simplifies integration for agencies processing large batches of script segments, as you receive complete audio data ready for immediate delivery or archival without managing complex state connections.

No Custom Cloning

The eight voices are fixed presets based on licensed recordings from LibriVox public-domain audiobook readings. We do not upload or clone customer voices, nor do we offer emotion tags or custom pronunciation lexicons. Each generated file carries an inaudible watermark identifying it as synthetic speech, which helps maintain transparency with end audiences.

Rate Limits

Your API key allows 60 requests per minute. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. Requests are processed sequentially, so under heavy load a synthesis job may wait in a queue before generating audio. Failed requests incur no charge, ensuring you only pay for successful generations.

Technical Limits

Contact and Support

Sound wave illustration for: Contact and Support

VerbaSync operates as an independent API storefront, so our support structure is built for efficiency rather than volume. We rely on asynchronous communication to ensure every localization agency query receives detailed, thoughtful attention without the noise of real-time interruptions.

Email Support Only

All inquiries are handled via email. This allows our team to reference specific request IDs, API logs, and billing details accurately before responding. Please include your API key prefix and a clear description of the issue for faster resolution.

No Phone Number

We do not offer a direct phone line. This keeps our operational overhead low and ensures you are never placed on hold. You can expect a written reply with full context, rather than a brief verbal summary.

No Live Chat

There is no live chat widget on this site. Our support team is available during standard business hours to assist with integration questions, voice selection, or billing discrepancies via email only.

Our Mission

Sound wave illustration for: Our Mission

VerbaSync exists to remove the friction between script and audio for localization teams. We provide a reliable TTS API that delivers consistent, licensable synthetic voices optimized for professional dubbing pipelines, allowing your team to scale production without the overhead of managing voice talent for every language.

Our goal is to make high-quality voice synthesis accessible to agencies of all sizes, ensuring that your creative vision is preserved across 23 languages with predictable, straightforward technology.

Democratizing Voice Synthesis

We believe that high-quality voice synthesis should not be limited by budget or scale. By offering a simple API with standard request shapes, we enable any developer or localization manager to integrate voice generation directly into their existing workflows without complex infrastructure.

Our voices are built on licensed recordings from LibriTTS-R, ensuring that the synthetic speech you generate is clear, natural, and ready for commercial use in your localized content.

Supporting Localizers

Localization agencies often face the challenge of maintaining voice consistency across multiple languages and projects. VerbaSync provides eight distinct voice presets that can be applied consistently, ensuring that your characters sound the same whether they are speaking English, Japanese, or Arabic.

We designed our API to fit into your existing dubbing pipelines, allowing you to generate audio files quickly and efficiently without the need for custom voice design or extensive post-production.

Our API supports 23 languages, allowing you to generate audio in any of them.

Transparent Pricing

We charge $10 per million characters, with no hidden fees or monthly plans. This straightforward pricing model allows you to predict your costs accurately, whether you are generating short phrases or long-form audio.

Failed requests are free, and your balance does not expire. You can top up with USDT on the TRON network, ensuring that your production can continue without interruption.

By eliminating the overhead of managing voice talent for every language, we help you focus on what matters most: delivering high-quality localized content to your audience.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Failed requests are free, ensuring you do not pay for errors.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. openai-python on GitHub
  3. IETF RFC 7845: Ogg Opus
  4. Creative Commons Attribution 4.0
  5. curl documentation
  6. MDN: Web Speech API
  7. LibriVox public-domain audiobooks
  8. ISO 639 language codes
  9. TRON developer hub: TRC-20
  10. Python documentation
  11. OpenAI API reference: create speech
  12. Node.js documentation

More on this site