Frequently asked questions
Who runs this website?
ShortForm AI operates this independent storefront for the text-to-speech API. We provide the infrastructure for creators to generate voiceovers programmatically.
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 structure mimics OpenAI’s speech endpoint for compatibility, but we use our own keys and infrastructure. We are an independent provider of text-to-speech synthesis services.
Where do the voices come from?
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings.
Is my data safe?
Input text is used only to produce the audio and is not used for training. Request metadata, including time, characters, and status, is kept for billing purposes. We do not store the generated audio files.
Do you store my generated audio?
No. Generated audio is returned in the response and not stored on our servers. Input text is used only to produce the audio and is not retained for training purposes. We keep request metadata for billing, but the actual audio files are delivered to you and not archived by us.
How do I contact support?
Support is by email only. You can reach us via the contact page or the email link provided in the footer.
Is there a phone number?
No. We do not provide a phone number for support. All customer inquiries are handled via email. This allows us to maintain a lean, engineering-focused operation.
Do you have a physical address?
No. We do not list a physical address. As an independent API provider, we operate digitally. All interactions, including billing and support, are managed online through our website and email channels without the need for a physical storefront.
Are the voices real people?
However, every generated file carries an inaudible watermark that marks it as synthetic speech. We do not offer custom voice cloning.
Can I sue if there is an error?
If synthesis fails, the charge is returned in full. Our service is provided as-is.
Do you offer refunds?
Yes. If synthesis fails, the charge is returned in full. Your balance does not expire.
Is the API open source?
No. You can use the OpenAI SDK or plain HTTP to interact with our endpoint.
What is the editorial team?
Do you use AI to generate voices?
No. Our voices are based on licensed recordings from LibriTTS-R and LibriVox. Every generated file carries an inaudible watermark that marks it as synthetic speech, distinguishing it from the original recordings.
Who we are
ShortForm AI is an independent storefront for a text-to-speech API. We understand the specific pacing and retention challenges of TikTok, Reels, and Shorts, ensuring our API generates voiceovers that match the rhythm of modern content.
Editorial team background
Focus on short-form video
We design our TTS engine specifically for creators making TikTok, Reels, and Shorts.
Engineering-led approach
We prioritize reliable, programmatic generation over manual recording. Our infrastructure handles text splitting and audio joining seamlessly, allowing no-code users to integrate high-quality audio into their workflows via simple API calls.
Voice licensing
We source our voice data from the LibriTTS-R dataset, which compiles readings from the public domain library.
LibriTTS-R source
Our voices are derived from LibriTTS-R, a high-quality dataset of spoken English.
CC BY 4.0 license
The underlying audio recordings are released under the Creative Commons Attribution 4.0 International license.
LibriVox public domain
The source material originates from LibriVox, a project where volunteers read books in the public domain.
Data policy
ShortForm AI processes your input text exclusively to generate the requested audio file. We do not use your voiceover scripts to train or improve our underlying synthesis models.
Text not used for training
Your input text is used only to produce the audio and is not used for training. We do not ingest your scripts to improve the model, keeping your content proprietary to your account.
Audio not stored
Generated audio is returned in the response and not stored. Once the file is delivered to your application, we do not retain a copy on our servers for later access or re-use.
Metadata kept for billing
Request metadata (time, characters, status) is kept for billing. This minimal data ensures accurate character counting and charge calculation for your account balance.
Technical limits
Our API follows a simple request-response model: you send text and receive a finished audio file. We do not support WebSocket connections or streaming partial audio chunks, so you cannot hear synthesis in progress as it happens.
The engine does not parse SSML tags, phoneme dictionaries, or custom pronunciation lexicons.
No streaming support
Synthesis is processed sequentially. You wait for the full audio file to be generated before receiving the response. This keeps infrastructure simple but means real-time partial output is not available.
No SSML support
We do not support SSML, phoneme dictionaries, or custom pronunciation lexicons.
No custom voice cloning
We do not offer custom voice cloning for customers, nor do you upload your own voice. The eight presets are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. You cannot design a new voice or clone a specific person's timbre for your projects.

Support channels
Email support only
Our support team handles all inquiries via email.
No live chat
We do not offer live chat widgets or instant messaging queues.
No phone number
There is no dedicated phone line or voice support channel. We respond to all messages promptly.
Contact us
Reach out with questions about the API, billing, or integration.
Use the form below or email us directly for specific technical or account issues.
Send email for inquiries
For general questions, billing issues, or technical support, send an email to our support address.
- General inquiries
- Billing and top-ups
- Technical support
Response time
High-volume periods may cause slight delays, but we prioritize all incoming tickets.
General feedback
If you have suggestions for the API or voice quality, we welcome your input.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Matching voice personas to your target demographic helps align audio tone with viewer expectations.
23 languages
Any voice speaks any of these languages.
