SpotLogic TTS API: Synthetic Voices for Advertising

By SpotLogic editorial team · Updated 2026-11-19

SpotLogic is a text-to-speech API built for advertising agencies that need broadcast-ready synthetic voices for radio spots and audio ads. This page explains our mission to deliver high-quality, clearly licensed audio at predictable prices, removing the overhead of traditional voice talent bookings. We use voices derived from the LibriTTS-R dataset, ensuring you receive professional narration without complex licensing disputes.

We focus on simplicity and transparency. You will find details on our data privacy practices, technical limitations, and how our support works. This is not a polished consumer product but a practical tool for agencies producing volume audio. Read on to understand exactly what we offer, what we do not, and how to integrate our API into your creative workflow.

SpotLogic TTS API: Synthetic Voices for Advertising

Frequently asked questions

Who runs SpotLogic?

SpotLogic is an independent storefront for the same text-to-speech API used across the network. Each site is an independent storefront for the same API. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.

Where do the voices come from?

Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0). These recordings originate from LibriVox public-domain audiobook readings. We use eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion.

Do you use the voices for training?

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. Request metadata (time, characters, status) is kept solely for billing purposes.

Do you store the generated audio?

No. Generated audio is returned in the response and not stored. We keep request metadata, such as time, character count, and status, only for billing purposes. Your input text is used exclusively to produce the audio and is not used for training.

How can I contact support?

Support is available by email only. We do not offer a phone number or live chat. You can reach us via the contact page at /contact/ on ah777.info. We aim to respond to your inquiries as quickly as possible via email.

Do you have a phone number?

No. We do not have a phone number. Support is provided via email only. You can contact us through the /contact/ page on our website. We do not offer live chat or phone support for any inquiries or technical issues.

Do you offer live chat?

No. We do not offer live chat. Support is handled exclusively through email. You can find the contact form on the /contact/ page. We do not maintain a phone number or live chat widget for customer assistance or technical support.

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 mimics the OpenAI speech endpoint structure, but we are an independent storefront. We use our own keys and billing system.

What is the CC BY 4.0 license?

CC BY 4.0 is a Creative Commons Attribution license. Our voices are based on LibriTTS-R recordings, which are licensed under CC BY 4.0. This allows commercial use provided you give appropriate credit. Check the specific license terms for your intended use case.

Can I use the voices for YouTube?

Yes. Our voices are based on LibriTTS-R (CC BY 4.0) from LibriVox public-domain audiobook readings. You can use the generated audio for YouTube videos. Ensure you comply with the CC BY 4.0 license requirements, which involve providing appropriate attribution to the source.

Can I use the voices for podcasts?

Yes. You can use the generated audio for podcasts. Our voices are based on LibriTTS-R (CC BY 4.0) from LibriVox public-domain audiobook readings. Ensure you comply with the CC BY 4.0 license requirements, which involve providing appropriate attribution to the source material.

Do I need to attribute the voices?

Yes, the CC BY 4.0 license requires attribution. Our voices are based on LibriTTS-R (CC BY 4.0) from LibriVox. This license typically requires attribution.

Is the API reliable?

Requests are processed one after another, so under load a request may wait in a queue. We do not offer an SLA or uptime guarantee. Typical speed is roughly real time for long texts. Short phrases may take a few seconds to generate.

Do you have an SLA?

No. We do not have an SLA or uptime guarantee. We do not offer enterprise contracts or on-premise installs. Our service is designed for predictable pricing and straightforward API access without the need for complex service level agreements or enterprise support tiers.

Our Mission

Sound wave illustration for: Our Mission

SpotLogic delivers broadcast-ready synthetic voices tailored for advertising agencies producing radio spots and audio ads. Our API enables teams to generate clear, licensable audio at scale without the overhead of studio bookings.

We focus on predictable pricing and high-quality voices that meet editorial standards. Agencies can produce content efficiently, ensuring every spot sounds professional and distinct.

Empowering Agencies

Empowering Agencies

Agencies often face tight deadlines and budget constraints when producing audio content. Our API allows teams to generate multiple variations quickly, testing different voices and speeds without booking studio time.

  • Produce multiple ad variations rapidly
  • Reduce dependency on studio schedules
  • Scale audio production with predictable costs

Affordable Audio

Affordable Audio

Pricing is straightforward: $10 per 1 million characters. Spaces and punctuation count, but failed requests are free. This model eliminates hidden fees, making budgeting for audio campaigns simple and transparent.

With a minimum top-up of $5 via USDT on the TRON network (TRC-20), agencies can start small and scale as needed. No monthly plans or minimum spend requirements mean you only pay for what you use.

  • $0.01 per 1,000 characters
  • Failed requests are free
  • No monthly plans or minimum spend

High-Quality Voices

High-Quality Voices

We provide eight presets based on licensed recordings from LibriTTS-R. Voices like Aria, Nova, and Felix offer distinct tones suitable for narration, promos, and conversational ads.

Each generated file carries an inaudible watermark, ensuring authenticity. The voices are clear, professional, and ready for broadcast use, meeting the standards of modern advertising.

  • 8 distinct voice presets
  • Licensed from LibriTTS-R
  • Broadcast-ready audio quality

Voice Licensing

Sound wave illustration for: Voice Licensing

The voices powering SpotLogic are derived from the LibriTTS-R dataset, which consists of public-domain audiobook readings from LibriVox. This foundation ensures that the synthetic voices used in your radio spots and audio ads are built on licensed, high-quality source material.

LibriTTS-R Source

LibriTTS-R Source

The underlying voice models are trained on recordings from the LibriTTS-R dataset. These recordings are sourced from LibriVox, a volunteer-based project providing free audiobooks. By leveraging these established public-domain readings, we ensure consistent voice quality across all eight presets.

CC BY 4.0 License

The LibriTTS-R dataset is distributed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This license allows for commercial use, which aligns with our target audience of advertising agencies producing broadcast-ready content. Attribution requirements are minimal, simplifying your compliance process.

Public Domain Basis

Since the source material originates from public-domain audiobooks, the underlying voice characteristics are free from restrictive copyright claims. This basis reduces legal ambiguity for agencies distributing audio ads across multiple platforms. You can integrate these voices into commercial projects with confidence, knowing the source rights are clear.

Data Privacy

Sound wave illustration for: Data Privacy

We process your input text solely to generate the requested audio file. The text is not used to train our models or improve voice quality, ensuring your ad scripts remain proprietary. Once the audio is generated and returned in the response, the original text is not stored for future reference.

Generated audio files are returned directly in the API response and are not persisted on our servers. Your creative assets exist only in your possession. We retain request metadata—such as timestamp, character count, and status—exclusively for accurate billing and usage tracking.

No Training on Input

Input text is used only to produce the audio and is not used for training.

No Audio Storage

Generated audio is returned in the response and not stored.

Billing Metadata Only

Request metadata (time, characters, status) is kept for billing.

Support

Sound wave illustration for: Support

SpotLogic provides support exclusively through email to keep operations lean and costs low for agencies. We do not maintain a live chat widget or a dedicated phone line for customer inquiries. This approach ensures that every question receives a thoughtful, written response from our technical team without the noise of instant messaging queues.

Our team prioritizes clear, documented solutions over real-time hand-holding. By removing the overhead of 24/7 voice support, we can offer the competitive pricing model that advertising agencies rely on for high-volume radio spot production. If you need immediate, synchronous assistance, you may need to integrate our API directly into your existing workflows.

Email Only

All support requests are handled via email. This single channel keeps communication organized and searchable, allowing you to reference previous technical details or API responses easily. There is no tiered support structure; every agency member has access to the same direct line to our engineers.

No Live Chat

You will not find a pop-up chat window on our dashboard or pricing page. We avoid the common industry practice of deflecting technical questions to automated bots or junior agents. Our email support is managed by staff who understand the specific nuances of TTS API integration for audio ads.

Response Time

During periods of high API traffic or maintenance, response times may vary slightly. For critical issues, please include your API key and request ID in your email to help us diagnose the problem quickly.

We do not offer an SLA or uptime guarantee. There is no guaranteed 15-minute response window, but we prioritize clarity and accuracy in every reply.

  • Standard response: within 24 hours
  • No guaranteed uptime or penalty SLA
  • Direct access to engineering staff
Support

Technical Limits

Sound wave illustration for: Technical Limits

SpotLogic delivers complete audio files rather than partial streams. Each request returns a finished MP3, WAV, or Opus file, which simplifies integration for agencies that need to download the final asset before editing or scheduling radio spots.

No Streaming

The API does not support WebSocket or real-time partial audio. Clients must wait for the full synthesis to complete before receiving the binary response. This design ensures consistent file integrity for broadcast workflows.

No SSML

Standard SSML tags like <break> or <prosody> are not parsed. Voice timing and emphasis are controlled solely through the speed parameter (0.25–4.0). For precise control, agencies should split text into separate requests.

No Custom Cloning

The platform does not offer voice cloning or custom voice uploads. Users select from eight licensed presets derived from LibriTTS-R. Each voice has a distinct character, but you cannot train a new voice based on your own recordings.

Contact Information

Sound wave illustration for: Contact Information

For all inquiries regarding the SpotLogic API, please direct your correspondence to [email protected]. This is our sole channel for customer communication, covering billing, technical questions, and account management for agencies using our text-to-speech services.

Email Address

Send your message to [email protected]. Our team handles all support requests via this address, ensuring a documented trail for your advertising agency’s records. We do not maintain a live chat widget or phone queue for general inquiries.

No Phone Number

We do not offer a telephone support line. All communication is asynchronous, allowing your team to receive detailed responses without waiting on hold. This structure supports agencies across different time zones without requiring immediate availability.

No Physical Address

SpotLogic operates as a cloud-based API service, so we do not maintain a public-facing physical office for client visits or package returns. Our infrastructure is distributed, and all technical and billing support is managed remotely via email.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Selecting the right format depends on your final distribution channel.

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. IETF RFC 7845: Ogg Opus
  3. openai-node on GitHub
  4. LibriTTS-R paper (arXiv 2305.18802)
  5. ISO 639 language codes
  6. openai-python on GitHub
  7. TRON developer hub: TRC-20
  8. Creative Commons Attribution 4.0
  9. FFmpeg documentation
  10. LibriTTS-R corpus (OpenSLR 141)
  11. Node.js documentation
  12. MDN: Web Speech API

More on this site