DubScript: A Reliable TTS API for Localization Agencies

By DubScript editorial team · Updated 2026-11-19

DubScript is a dedicated text-to-speech API built for localization agencies managing high-volume multilingual projects. We focus on providing a reliable, transparent tool for publishers who need consistent audio generation without enterprise overhead.

You will find details on our technical limitations, such as the absence of streaming or SSML support, and our commitment to honest, specific communication. Whether you are integrating via the OpenAI-compatible SDK or using raw HTTP requests, this guide clarifies how DubScript fits into your production workflow. Read on to understand our philosophy, data handling, and how to reach our support team.

DubScript: A Reliable TTS API for Localization Agencies

Frequently asked questions

Who runs this website?

This is an independent storefront for the DubScript text-to-speech API. We provide the cloud service directly to agencies and publishers. Each site in our network operates independently, offering the same API endpoint and pricing structure. We are a standalone provider focused on delivering reliable multilingual audio generation for high-volume localization projects.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint mirrors the OpenAI speech endpoint structure, allowing you to use official OpenAI SDKs by simply changing the base URL. We are a separate company providing a compatible alternative for text-to-speech generation, using our own infrastructure and voice models.

What licenses apply to the voices?

Our voices are based on licensed recordings from LibriTTS-R, which is available under the Creative Commons Attribution 4.0 (CC BY 4.0) license. Additionally, every generated audio file contains an inaudible watermark to mark it as synthetic speech. These are the primary licensing details governing the voice assets used in our API.

Can I use the voices in commercial projects?

Yes, you can use the generated audio in commercial projects. The voices are derived from LibriTTS-R (CC BY 4.0) and LibriVox public-domain readings.

Do you store my input text?

Your input text is used only to produce the audio and is not used for training our models. Generated audio is returned in the response and not stored. We retain request metadata, such as time, character count, and status, strictly for billing purposes and to manage your account usage effectively.

How can I contact support?

Support is available via email only. We do not offer a phone number, live chat, or dedicated support line. You can reach our team through the contact page on this site. We aim to address inquiries efficiently, but response times may vary depending on the volume of support requests we receive.

Do you have a physical office?

Our team manages the API infrastructure and support remotely. If you require specific business details, you can find our contact information on the /contact/ page of this website for direct communication.

Are you certified under GDPR or SOC 2?

We do not hold specific certifications such as SOC 2, HIPAA, or GDPR certificates. We do not provide an SLA or uptime guarantee. Our data practices are standard for our scale, but we do not publish third-party audit reports. We recommend reviewing our data handling details on the /about/ page for specifics.

Our Editorial Team

Sound wave illustration for: Our Editorial Team

We are an editorial team composed of voice-over and localization experts who understand the practical demands of high-volume audio production. Our background spans script adaptation through to final delivery, ensuring our API solves real workflow bottlenecks rather than adding new ones.

Composed of voice over and localization experts

Composed of voice over and localization experts

Our core team has spent years managing multilingual audio projects, from initial script adaptation to final voice-over delivery. We built DubScript because existing tools lacked the transparency and volume handling required for professional localization pipelines.

Focus on practical API solutions for agencies

Focus on practical API solutions for agencies

We prioritize utility over hype. Our platform delivers reliable, batch-friendly audio generation with clear pricing, designed specifically for agencies processing thousands of characters daily without unexpected delays or hidden costs.

Independent editorial voice, not affiliated with major brands

Independent editorial voice, not affiliated with major brands

We operate independently, maintaining an editorial stance that avoids brand bias. We are not affiliated with OpenAI, ElevenLabs, or other major voice providers, allowing us to focus purely on the technical reliability and cost-efficiency our clients require.

Voice Licensing and Sources

Sound wave illustration for: Voice Licensing and Sources

DubScript provides a reliable text-to-speech API tailored for agencies managing high-volume dubbing and localization projects. Our platform streamlines the production of multilingual audio assets with transparent pricing and standard developer tools.

Voices based on LibriTTS-R (CC BY 4.0)

Voices based on LibriTTS-R (CC BY 4.0)

Our eight voice presets are derived from the LibriTTS-R dataset, which is licensed under CC BY 4.0. This foundation ensures that every generated audio file carries an inaudible watermark marking it as synthetic speech.

Recordings from LibriVox public-domain audiobooks

The underlying recordings originate from LibriVox, a collection of public-domain audiobook readings. By leveraging these established sources, we ensure consistent vocal quality across all 23 supported languages, from English and Spanish to Japanese and Swahili, without requiring custom voice design.

Clear licensing for commercial use

Agencies can integrate these voices into commercial localization projects with confidence. This clarity simplifies legal reviews for high-volume production pipelines.

Data Policy and Privacy

Sound wave illustration for: Data Policy and Privacy

DubScript operates with a transparent data policy designed for localization agencies handling sensitive scripts. We prioritize clarity regarding how your input data is processed, ensuring you retain control over your voice assets without unexpected secondary uses.

Input text not used for model training

Your source text is processed solely to generate the requested audio file. Unlike many consumer-grade TTS providers, we do not use your input text to train or improve our underlying models. Your scripts remain yours.

Generated audio not stored by default

The synthesized audio files are returned directly in the API response and are not persistently stored by our systems. Once delivered to your endpoint, the audio data is transient, reducing your risk of storing sensitive voice assets on our servers.

Metadata kept only for billing purposes

We retain minimal metadata—specifically request timestamps, character counts, and status codes—strictly for billing and usage verification. This ensures accurate invoicing based on your actual consumption without retaining the content of your translations or voiceovers.

Product Philosophy

Sound wave illustration for: Product Philosophy

DubScript operates with an editorial tone, avoiding marketing fluff. We provide transparent, specific details about our API’s capabilities and limitations, ensuring agencies can make informed decisions based on facts rather than hype.

Honest, specific, no hype marketing

We avoid superlatives unless supported by data. Our descriptions focus on what the product actually does, such as processing 4096-character inputs or supporting 23 languages, without exaggerating performance or quality.

  • Clear, factual descriptions of features
  • No exaggerated claims about speed or quality
  • Transparent pricing and limits

No superlatives without factual basis

Every claim is grounded in verifiable facts. For instance, we state that our API processes requests at roughly real-time speeds (about 25 characters per second), rather than using vague terms like 'lightning fast'.

Focus on utility for localization agencies

Our platform is designed for agencies managing high-volume dubbing projects. We prioritize reliability and standard developer tools, such as OpenAI SDK compatibility, to streamline multilingual audio asset production without unnecessary complexity.

  • Streamlined workflow for high-volume projects
  • Standard developer tools integration
  • Reliable API for localization needs
Product Philosophy

Contact and Support

Sound wave illustration for: Contact and Support

DubScript was built by voice-over and localization specialists who understand the specific workflows of agency teams. Our editorial team focuses on practical API solutions rather than marketing hype, ensuring our product remains a reliable tool for high-volume dubbing projects. We maintain an independent voice, distinct from major brand affiliations, to provide clear, factual documentation for publishers and developers.

We prioritize transparency in our support structure. By keeping our team lean and focused on product development, we ensure that every interaction is meaningful and directly addresses the technical needs of localization agencies.

Support available via email only

All support inquiries are handled exclusively through email. This approach allows our team to provide detailed, thoughtful responses tailored to your specific integration or usage question without the distractions of real-time chat.

Email support is the single channel for both technical and billing issues.

  • Email is our only support channel
  • No live chat widget on the site
  • Responses are detailed and reference-specific

No phone number or live chat

We do not maintain a dedicated phone line or real-time live chat service. This decision reflects our focus on asynchronous, documented communication that aligns with how developers and localization managers typically work. It ensures that support conversations are searchable and easily referenced later in your project history.

Unlike traditional agencies that rely on voice calls for quick checks, our email-first model allows us to provide precise answers with attached documentation or code snippets when necessary.

Response times may vary during peak load

During periods of high demand or major updates, response times may vary. While we strive to address all inquiries promptly, complex technical issues may require additional review time.

We recommend including your API key prefix and specific error logs in your initial email to help our team diagnose issues faster. For urgent billing matters, please specify your account email for quicker identification.

  • Response times vary during peak load
  • Include API key prefix in queries
  • Attach error logs for technical issues

Technical Limitations

Sound wave illustration for: Technical Limitations

DubScript is designed as a straightforward text-to-speech API rather than a real-time streaming service. It does not support WebSocket connections or partial audio streaming, meaning you receive the complete audio file only after synthesis finishes. This request-response model suits batch processing workflows common in localization projects.

No streaming or WebSocket support

Since audio is generated in full before delivery, large texts require splitting and joining. This approach ensures consistent quality but introduces latency compared to true streaming solutions.

No SSML or custom pronunciation support

The API does not interpret SSML tags or allow custom pronunciation lexicons. Voice output relies on standard text input and the eight preset voices. For specific pronunciation needs, you must adjust the input text manually before sending it to the endpoint.

Rate limits apply per API key

Each API key is limited to 60 requests per minute, or 10 per minute before the first top-up. Under heavy load, requests may queue, extending generation time. Plan your integration to handle these limits gracefully, especially when processing high-volume dubbing batches.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The gender balance allows for multi-character dialogue generation without relying on third-party voice cloning services.

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. curl documentation
  3. IETF RFC 7845: Ogg Opus
  4. Creative Commons Attribution 4.0
  5. MDN: Web Speech API
  6. Node.js documentation
  7. Python documentation
  8. W3C WAI: making audio and video accessible
  9. FFmpeg documentation
  10. ISO 639 language codes
  11. openai-node on GitHub
  12. OpenAI API reference: create speech

More on this site