Build Your Podcast Voice With Our Indie TTS API

By PodcastVoice API editorial team · Updated 2026-11-18

This page explains who we are and why we built PodcastVoice API. We are an independent team focused on serving freelance podcasters and audio content creators who need high-quality, multilingual voiceovers without the overhead of a full studio. You will find details about our technology, voice licensing, data privacy, and support structure.

We provide a simple, transparent API that turns your scripts into broadcast-ready audio files. Our approach is built for freelancers who value honesty, specific features, and clear pricing. Read on to understand how our indie TTS solution fits into your creative workflow.

Build Your Podcast Voice With Our Indie TTS API

Frequently asked questions

What is PodcastVoice API?

PodcastVoice API is a cloud text-to-speech service for podcasters. Send text via POST to receive audio files. It uses standard endpoints compatible with OpenAI SDKs. You get broadcast-ready audio in formats like mp3, wav, opus, flac, or pcm. It is designed for freelance creators who need simple, high-quality voiceovers without studio overhead.

Who runs the site?

We are an independent storefront for the same TTS API network. This site is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We operate as a standalone provider, offering transparent pricing and direct API access for content creators who prefer a focused tool over large platform ecosystems.

How are voices licensed?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0). These originate from LibriVox public-domain audiobook readings. Every generated audio file carries an inaudible watermark marking it as synthetic speech. This ensures clear provenance while providing high-quality, natural-sounding voices for your podcast episodes.

Is my data safe?

Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and not stored. We keep request metadata like time, characters, and status for billing purposes. Your scripts remain private and are processed solely for the immediate generation of your audio files.

Do you guarantee uptime?

No, we do not offer an SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time, but short phrases may take a few seconds. We provide reliable service, but no formal guarantees on availability or latency.

How do I contact support?

Support is available by email only. We do not offer live chat, phone support, or a dedicated phone number. Support is by email only. We aim to respond to inquiries promptly to help you resolve any issues.

Do you have a phone number?

No, we do not have a phone number. All support is handled via email. This keeps our operations lean and focused on delivering a high-quality API experience. Support is by email only.

Are you affiliated with OpenAI?

No, we are not affiliated with OpenAI. Our API endpoint shape matches the OpenAI speech endpoint, so their SDKs work by changing the base URL. However, we are an independent provider. We do not use OpenAI’s infrastructure, branding, or models. We are a separate entity serving podcasters directly.

Do you offer custom voices?

No, we do not offer custom voice cloning or uploading your own voice. We provide eight preset voices based on licensed recordings. These include female options like Aria and Nova, and male options like Felix and Milo. Each voice has a distinct tone, but you cannot create a unique voice clone.

Do you store generated audio?

No, generated audio is returned in the response and not stored on our servers. Input text is also not stored for training purposes. We retain request metadata such as time, character count, and status for billing and usage tracking. Your audio files are delivered directly to you and then discarded.

Is the API secure?

Yes, authentication uses a Bearer token via the Authorization header. Each account has one active key, which can be revoked instantly. Data is transmitted securely, and input text is not used for training. We maintain a straightforward security model suitable for freelance creators integrating voice synthesis into their production workflows.

What is your mission?

We provide a simple, transparent API for freelance podcasters and audio creators. Our goal is to enable high-quality, multilingual voiceovers without the overhead of a full studio. We focus on clear pricing, easy integration, and reliable performance, empowering creators to produce professional audio content efficiently and affordably.

Do you offer refunds?

Failed requests are free, with the charge returned in full if synthesis fails. For successful requests, we do not explicitly mention refunds beyond the failed request policy. Your balance does not expire. You can manage your key and billing directly through your account dashboard on the /get-api-key/ page.

How do I get help?

You can get help by emailing our support team. There is no phone number or live chat. Detailed documentation is available at /docs/, and you can manage your API key and usage on /get-api-key/. For billing or technical issues, our email support is the primary channel for assistance.

Who We Are

Sound wave illustration for: Who We Are

We are a small team of audio engineers and developers who understand the grind of freelance podcasting. We built PodcastVoice API because we needed a reliable, transparent tool for our own projects, and we share that same drive with you.

Indie Focus

Indie Focus

We operate without corporate overhead, keeping our pricing straightforward and our support personal. You get direct access to the people who maintain the API, ensuring your voiceovers stay on schedule.

Freelancer Friendly

Freelancer Friendly

Designed for independent creators, our API fits seamlessly into your existing workflow. Whether you are using Python, JavaScript, or plain HTTP, our OpenAI-compatible endpoint requires minimal setup. You can start generating broadcast-ready audio in minutes without hiring a specialist.

Creator First

Creator First

Every feature is chosen to serve the content creator. We prioritize clear, high-quality voices that sound natural in long-form audio, from 8 presets to 23 languages. Our pricing model scales with your usage, so you only pay for what you produce.

Our Technology

Sound wave illustration for: Our Technology

PodcastVoice API is built as a straightforward cloud interface: you send text and receive an audio file. It uses standard HTTP requests, meaning you do not need a custom library or SDK to get started. The entire workflow fits into a single API call, keeping your integration clean and predictable.

API Based

API Based

We provide a simple RESTful endpoint that accepts JSON payloads and returns audio directly. There are no complex WebSocket streams or real-time partial audio chunks to manage. You submit your script, and the service returns the finished broadcast-ready file, ready for your podcast workflow.

OpenAI Compatible

Our endpoint mirrors the OpenAI speech structure, so you can use the official OpenAI SDKs by simply changing the base URL to https://api.get28s.com/v1. This means your existing code works with minimal adjustments. We use the same request shape for models like 'tts-1' and 'tts-1-hd'.

  • Same JSON body as OpenAI's speech endpoint
  • Works with official OpenAI SDKs
  • No proprietary format required

Simple Integration

Integration takes minutes. You only need your API key and a text input. The system handles voice selection, language detection, and format conversion automatically. You can start generating audio with a single curl command or a few lines of Python, without managing complex configuration files.

Voice Licensing

Sound wave illustration for: Voice Licensing

The voices powering PodcastVoice API originate from the LibriTTS-R dataset, derived from public-domain audiobook recordings available on LibriVox. This foundation ensures that our 8 voice presets—like Aria, Nova, and Felix—are built on licensed, high-quality human speech rather than synthetic approximations.

The source recordings are based on licensed recordings: LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. The source material is carefully curated to provide clear, broadcast-ready narration suitable for podcast intros, segments, and voiceovers.

LibriTTS-R Source

Our voices are based on licensed recordings from the LibriTTS-R dataset. This collection features professional-grade audio samples extracted from public-domain audiobooks, providing a natural and expressive base for our text-to-speech engine. The dataset offers diverse intonations and pacing, ensuring that your podcast scripts sound engaging and human.

  • Derived from high-quality LibriVox recordings
  • Optimized for narrative clarity and tone
  • Supports 8 distinct voice presets

CC BY 4.0 License

The underlying voice models operate under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means you are free to share and adapt the audio for commercial purposes, including monetized podcasts and YouTube videos. The source material is licensed under CC BY 4.0, which typically requires attribution to the original source (LibriVox/LibriTTS-R).

  • Commercial use permitted
  • No royalty fees per download
  • Simple attribution requirements

Public Domain Audio

The source recordings come from public domain audiobooks, ensuring that the foundational audio is free from restrictive copyright claims. This reduces the risk of content ID strikes or licensing disputes on your content. You can focus on creating your story without worrying about the legal intricacies of the voice's origin.

  • Based on public-domain audiobook readings
  • Reduces content ID strike risks

Data Privacy

Sound wave illustration for: Data Privacy

We respect your creative ownership. Input text is used exclusively to generate your audio files and is never added to our training datasets. Once the audio is returned in the response, it is not stored on our servers, ensuring your scripts remain yours.

Your data flows through secure connections during synthesis. We retain only request metadata—such as timestamp, character count, and status—for accurate billing and usage tracking. No personal content lingers in our systems after delivery.

Audio files are generated on-demand and returned directly to your application. We do not keep copies of your spoken scripts or the resulting audio files, so your creative work stays private and under your control.

No Training Data

Your input text is used solely to produce the audio file for your specific request. We do not use your scripts to train or improve our models, meaning your creative words remain distinct from our training data.

No Audio Storage

Generated audio is returned in the response and not stored. We do not keep copies of your spoken scripts or the resulting audio files, so your creative work stays private and under your control.

Secure Processing

We retain only request metadata—such as timestamp, character count, and status—for accurate billing and usage tracking. No personal content lingers in our systems after delivery.

Data Privacy

Our Limits

Sound wave illustration for: Our Limits

We run a lean operation built for creators, not enterprise contracts. This means we skip the bells and whistles of guaranteed availability and premium support tiers. We focus our resources on keeping the API reliable and the pricing transparent.

Understanding our limitations helps you plan your production workflows accurately. There are no SLAs, no uptime guarantees, and support is handled entirely via email.

No SLA

We do not offer a Service Level Agreement. While we strive for consistent performance, we do not contractually guarantee specific response times or availability metrics.

Our infrastructure is optimized for cost-effective scaling rather than enterprise-grade redundancy. If you require a legally binding SLA with financial penalties for downtime, this indie API may not fit your compliance needs.

No Uptime Guarantee

We do not publish a 99.9% or higher uptime guarantee. Occasional latency or brief outages can occur, especially during peak usage times when requests queue up.

Since we process requests sequentially without massive parallel clusters, you may experience delays if the queue is long. We prioritize fairness over guaranteed instantaneous delivery.

Standard Support

Support is provided via email only. We do not have a phone number or live chat to keep overhead low.

Support is by email only. For urgent issues, please include your API key and request ID in your message to help us diagnose the problem quickly.

  • Email-only support
  • No phone number
  • No live chat

Contact Us

Sound wave illustration for: Contact Us

PodcastVoice API is a small, independent operation built by creators for creators. We skip the corporate overhead to keep our API simple, transparent, and affordable for freelance podcasters and audio producers who just want to get work done.

Since we are a lean team, we don’t offer phone lines or live chat. Instead, we provide direct, human email support where you can ask about billing, voices, or integration details without waiting on hold.

Email Support

Our support team handles all inquiries via email. We aim to respond to every message promptly, ensuring that freelancers and small studios get clear answers to their technical or billing questions.

No Phone Number

You won’t find a phone number on this site. We prefer asynchronous communication, which allows us to document issues thoroughly and provide you with written references you can keep for your records.

Get in Touch

Reach out directly for any questions about the PodcastVoice API. Whether you need help with your API key, have a question about voice licensing, or want to discuss your next audio project, we are here to help.

Send us a message and we’ll get back to you as soon as possible.

  • Direct email support
  • No wait times on hold
  • Written records of all conversations

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. The price difference is non-existent, making the choice purely about aesthetic preference.

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. W3C WAI: making audio and video accessible
  3. MDN: Web Speech API
  4. Python documentation
  5. ISO 639 language codes
  6. curl documentation
  7. LibriVox public-domain audiobooks
  8. OpenAI API reference: create speech
  9. FFmpeg documentation
  10. openai-python on GitHub
  11. LibriTTS-R corpus (OpenSLR 141)
  12. Node.js documentation

More on this site