Your Professional Voiceover Solution for YouTube Creators

By AudioScribe editorial team · Updated 2026-11-18

AudioScribe is an independent storefront for a cloud text-to-speech API, built specifically for no-code YouTube creators. This page explains our origins, the licensing behind our voices, and how we handle your data. You will find clear details on our technical foundation, support structure, and honest limits without marketing hype.

We help you turn scripts into high-quality voiceovers without hiring actors or learning complex editing tools. Our API integrates directly into your workflow to automate narration for videos, shorts, and tutorials. Read on to understand exactly how our service works, who powers our voices, and why we keep things simple for creators like you.

Your Professional Voiceover Solution for YouTube Creators

Frequently asked questions

Are you affiliated with OpenAI?

No. We are an independent storefront for a text-to-speech API. While our endpoint structure mimics the OpenAI speech endpoint for easy integration, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. We use our own keys and infrastructure.

Who owns the voices?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We do not own the original recordings but have licensed them for use in our synthetic speech engine. The generated audio files carry an inaudible watermark marking them as synthetic speech.

Do you store my generated audio?

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) only for billing purposes. Your actual audio files are not retained on our servers.

Can I use the voices commercially?

Yes. The underlying recordings are from LibriVox public-domain audiobooks, and the TTS service is available for commercial use. You can use the generated audio for YouTube videos, shorts, tutorials, and other commercial projects.

How do you license the voices?

The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This allows us to offer high-quality synthetic speech while respecting the original creators' rights under the Creative Commons Attribution 4.0 International license and public domain status.

Do you have a physical office?

We do not list a physical office address. We are an independent digital storefront for the AudioScribe API. Support is provided via email only. We do not have a phone number, live chat, or physical location for customer visits. All operations are managed remotely.

Can I request a new voice?

No. We do not offer custom voice design or voice cloning for customers. You cannot upload your own voice or request new presets. We currently offer eight fixed voice presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These are the only available options.

Do you offer refunds?

Failed requests are free; if synthesis fails, the charge is returned in full. However, we do not offer general refunds for successful requests. Balance does not expire, and there are no monthly plans or subscriptions. You pay only for the characters you successfully generate.

Is my data secure?

Input text is used only to produce the audio and is not used for training. Generated audio is not stored. We keep request metadata for billing. We do not offer SLAs or uptime guarantees.

Can I get a custom voice?

No. We do not offer custom voice cloning, uploading your own voice, or voice design. You must choose from our eight preset voices. Each generated file carries an inaudible watermark.

Do you have a mobile app?

No. We do not have a mobile SDK or a dedicated mobile app. You can use our API via the official OpenAI SDKs by changing the base_url, or via plain HTTP requests. There is also no WordPress plugin or browser extension available for direct use.

Can I use the API for live streaming?

No. We do not offer streaming, WebSocket, or real-time partial audio. Requests are processed one after another, so under load a request may wait in a queue. It is better suited for pre-rendered videos, shorts, and tutorials rather than live streaming scenarios.

Do you offer enterprise plans?

No. We do not offer enterprise contracts, SLAs, or dedicated support tiers. There are no monthly plans, seats, or minimum spend requirements. You pay based on usage ($10 per 1 million characters). Support is available by email only for all users.

How do I contact support?

Support is by email only. We do not have a phone number, live chat, or physical office. You can reach us via the contact page or by emailing our support team.

Who We Are

Sound wave illustration for: Who We Are

AudioScribe is an independent storefront for the same text-to-speech API used by creators worldwide. We focus exclusively on helping YouTube creators turn scripts into high-quality voiceovers without hiring voice actors or learning complex editing tools.

Our API integrates directly into your workflow to automate narration for videos, shorts, and tutorials. We provide a simple, no-code friendly experience that fits seamlessly into your existing production process.

Independent Storefront

Independent Storefront

We are not affiliated with OpenAI, ElevenLabs, or any other brand. We operate as a direct retailer of the underlying TTS API, offering transparent pricing and direct access to the technology you need.

Our platform is designed to be straightforward and reliable, ensuring you get exactly what you need without unnecessary complexity or hidden fees.

  • Direct API access
  • Transparent pricing
  • No middlemen

Focus on YouTube Creators

Focus on YouTube Creators

We understand the unique needs of YouTube creators. Our API is optimized for generating narration that sounds natural and engaging, perfect for videos, shorts, and tutorials.

By automating the voiceover process, you can produce content faster and more consistently, allowing you to focus on creativity and storytelling.

  • Optimized for YouTube content
  • Natural-sounding narration
  • Consistent output

No-Code Friendly

No-Code Friendly

Our API is designed to be easy to use, even if you don't have a technical background. Simply send text and receive audio files without needing to manage complex infrastructure.

With simple HTTP requests and clear documentation, you can integrate our TTS into your workflow quickly and efficiently.

We provide ready-to-use examples and straightforward endpoints, making it easy to get started without diving into code.

  • Simple HTTP requests
  • Clear documentation
  • Ready-to-use examples

Voice Licensing

Sound wave illustration for: Voice Licensing

AudioScribe provides a transparent TTS API tailored for YouTube creators who value clear attribution. Our voice models are derived from high-quality licensed recordings, ensuring that the synthetic speech you generate is built on solid, verifiable foundations without hidden licensing traps.

LibriTTS-R Source

LibriTTS-R Source

Our eight voice presets—Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion—are based on the LibriTTS-R dataset. This source provides a diverse range of vocal textures, from warm narrators to energetic promo styles, giving you the flexibility to match your video’s tone precisely.

CC BY 4.0 License

The voice presets are based on the LibriTTS-R dataset (CC BY 4.0) and LibriVox public-domain recordings.

  • Commercial use allowed
  • Simple attribution required

LibriVox Public Domain

Many of the base recordings originate from LibriVox, a project dedicated to public domain audiobooks. By leveraging these freely available public domain readings, we ensure that the core vocal characteristics are free from restrictive copyright claims, allowing you to focus on content creation.

Data Policy

Sound wave illustration for: Data Policy

AudioScribe is an independent storefront for a text-to-speech API, meaning your data handling reflects our specific operational scope rather than that of a large tech conglomerate. We prioritize transparency for creators who want clear rules about how their content is processed.

Our approach is designed to keep your creative assets secure while ensuring we can accurately bill for the compute resources used to generate your voiceovers.

Text Not Used for Training

Your input text is used exclusively for the purpose of generating the audio file. We do not use your scripts, dialogue, or narration content to train or improve our underlying neural models. Once the audio is generated, the text is not retained for model learning purposes.

No Audio Storage

The generated audio file is returned directly in the API response and is not stored on our servers for long-term retention. We do not keep copies of your voiceovers to build a library or use them for other purposes. This ensures your audio content remains transient and under your control.

Metadata Kept for Billing

We retain request metadata, including the timestamp, character count, and status (success or failed), primarily for accurate billing and troubleshooting. This minimal data allows us to verify usage against your account balance and issue refunds for failed requests without needing to store the actual audio content.

Honest Limits

Sound wave illustration for: Honest Limits

We prioritize stable, batch-based synthesis over real-time streaming. Requests are processed sequentially, so under load, your audio may wait in a queue. This ensures consistent quality and predictable pricing without the complexity of WebSocket connections or partial audio chunks.

No Streaming or WebSocket

We do not offer real-time streaming or WebSocket endpoints. The API returns complete audio files once synthesis is finished. This batch approach simplifies integration for no-code tools and ensures you receive a complete audio file.

No Custom Voice Cloning

We provide eight high-quality preset voices derived from licensed recordings, but we do not offer custom voice cloning. You cannot upload your own audio to create a unique voice model. This keeps our service simple, reliable, and focused on the eight curated presets that speak all 23 supported languages.

No SLA or Uptime Guarantee

As an independent storefront, we do not offer Service Level Agreements (SLAs) or formal uptime guarantees. Our infrastructure is designed for high reliability, but we do not contractually promise specific availability percentages. This allows us to keep costs low and direct all resources toward API performance and voice quality.

Honest Limits

Support Contact

Sound wave illustration for: Support Contact

AudioScribe is a small, independent storefront, so we keep our support team lean and focused on you. We believe in clear, thoughtful answers rather than rushed interactions. When you reach out, you can expect a response from our support team.

Email Only Support

Our primary and only channel for support is email. This allows us to provide detailed, accurate answers without the pressure of real-time chat. You can send your questions, code snippets, or billing issues to our support team, and we will get back to you as quickly as possible.

No Live Chat

We do not offer live chat widgets on our site. This helps us maintain a calm, focused environment for resolving technical issues. Your message will be handled by our support team.

No Phone Number

There is no phone number for AudioScribe. We have chosen asynchronous communication to ensure every question gets the attention it deserves. If you need immediate assistance during a video recording session, email is still the most reliable way to get a clear, written solution.

Technical Details

Sound wave illustration for: Technical Details

AudioScribe uses a standard REST API compatible with the official OpenAI SDK. Developers can integrate by setting the base URL to https://api.je1688.com/v1. This allows you to use familiar SDK methods while sending requests to our independent endpoint.

OpenAI SDK Compatible

You can use the official OpenAI SDKs by simply changing the base_url to https://api.je1688.com/v1. This allows you to use familiar SDK methods while sending requests to our independent endpoint.

REST API Structure

The API follows a predictable REST structure. Send a POST request to /v1/audio/speech with a JSON body. Other endpoints like /v1/voices provide metadata. The request shape matches the OpenAI speech endpoint exactly.

Standard Authentication

Include your API key in the Authorization: Bearer tts-... header. Each account has one active key. You can issue a new key at any time, and the old one stops immediately.

  • Base URL: https://api.je1688.com/v1
  • Endpoint: POST /v1/audio/speech
  • Auth: Bearer token in header

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Viewers expect factual delivery without emotional bias, making voice selection critical for trust.

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. Node.js documentation
  3. curl documentation
  4. LibriVox public-domain audiobooks
  5. openai-node on GitHub
  6. Python documentation
  7. openai-python on GitHub
  8. Creative Commons Attribution 4.0
  9. FFmpeg documentation
  10. TRON developer hub: TRC-20
  11. LibriTTS-R corpus (OpenSLR 141)
  12. OpenAI API reference: create speech

More on this site