Frequently asked questions
Who runs this site?
An independent team operates this storefront for the SpeakFlow TTS API. We are not affiliated with OpenAI, ElevenLabs, or any other brand. This is a standalone service designed for no-code creators, providing direct access to the API without enterprise contracts or complex infrastructure requirements.
Are the voices licensed?
Yes. Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Every generated audio file also includes an inaudible watermark to clearly mark it as synthetic speech, ensuring transparency about the audio's origin.
Is my data used for training?
No. Your input text is used solely to produce the requested audio file and is not used for training models. We do not store the generated audio after it is returned in the response. Only request metadata, such as time and character count, is kept for billing purposes.
Do you store audio files?
No. Generated audio is returned directly in the API response and is not stored on our servers. We retain only request metadata, including the timestamp, character count, and status, which is necessary for accurate billing and tracking your usage against your account balance.
How do I contact support?
Support is available via email only. We do not offer a phone number, live chat, or SLA. You can reach us through the contact page.
Is this site official?
This is an independent storefront for the SpeakFlow API. We are not affiliated with OpenAI, Google, Amazon, or Microsoft. While our API endpoint shape matches the OpenAI speech endpoint, we are a separate entity. Our voices are based on LibriTTS-R recordings.
What is the data retention policy?
Input text is processed only for synthesis and not retained. Generated audio is not stored. We keep request metadata (time, characters, status) for billing purposes. This data supports your account balance tracking and usage history. No other personal data is stored beyond what is needed for your API key and account.
Can I use voices commercially?
Yes. The underlying voices are based on LibriTTS-R (CC BY 4.0) from LibriVox public-domain audiobook readings. You can use the generated audio for commercial purposes, such as online courses, LMS platforms, or marketing. Each file includes a synthetic watermark to identify it as AI-generated speech.
Who we are
SpeakFlow is an independent team building a straightforward cloud API for text-to-speech generation. We focus on delivering reliable audio files for online courses, designed specifically for no-code creators who need predictable, character-based pricing without managing complex infrastructure.
Our API allows you to convert course scripts into audio files. We prioritize practical utility and transparent pricing, ensuring that creators can integrate speech synthesis without unnecessary technical overhead.
Independent editorial team
We operate independently, distinct from the major tech giants. Our team manages the API infrastructure and documentation directly, ensuring that updates and pricing changes are communicated clearly without corporate bureaucracy.
- Direct management of the TTS API
- No corporate parent company
- Transparent pricing models
Focus on no-code users
SpeakFlow is built for creators who may not write code daily. Our API endpoint mimics the familiar OpenAI structure, allowing easy integration using standard HTTP requests or existing SDKs. This design choice reduces the learning curve for integrating audio into course materials.
- Simple JSON API
- Compatible with common HTTP clients
- No complex infrastructure required
Practical documentation
Our documentation provides concrete examples for converting text to speech. We include ready-to-use curl commands and clear explanations of request parameters like voice selection and language codes. This ensures you can generate audio for your courses quickly and accurately.
- Ready-to-use code examples
- Clear parameter explanations
- Direct API integration guides
Voice licensing
Our voice presets are built from licensed recordings, ensuring clear, high-quality synthetic speech for your course audio. Each voice is derived from specific source material to provide distinct tonal characteristics.
We use standard recordings rather than custom-designed voices, keeping the technology straightforward and reliable for no-code creators who just need consistent audio output without complex infrastructure or licensing headaches.
LibriTTS-R recordings
All eight voice presets are based on the LibriTTS-R dataset. This provides a consistent base for our synthetic speech engine, ensuring that every generated file maintains high audio quality across different languages and speeds.
CC BY 4.0 license
The underlying voice data is licensed under CC BY 4.0. This standard open license allows us to process and synthesize the audio for your use while respecting the original creators' attribution requirements.
LibriVox source
The recordings originate from LibriVox, a platform for public-domain audiobook readings. By leveraging these public-domain sources, we ensure that the core voice materials are freely available for reuse and modification, keeping our infrastructure simple and cost-effective.
Data privacy policy
We prioritize your data integrity with a straightforward policy. Your input text is used exclusively to generate the audio response and is never used for training our models. This ensures that your unique course scripts remain yours, without being ingested into our training datasets for future model improvements.
Input text not trained
When you send a request, the text is processed solely to produce the audio file returned in the response. We do not retain the content of your scripts for machine learning purposes, keeping your proprietary course material distinct from our engine's development data.
No audio storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Once the file is transmitted to your client, it is not kept in our long-term storage, minimizing the risk of audio data retention.
Billing metadata kept
We retain request metadata—such as timestamp, character count, and status—strictly for billing and usage verification. This data ensures accurate character counting and chargeback resolution but does not include the actual content of your text or the generated audio.
Technical limitations
SpeakFlow provides a straightforward REST API for generating audio from text. This design choice keeps the service simple and reliable for no-code creators, but it means you cannot stream audio chunks in real-time as they are generated.
No streaming audio
The API returns a complete audio file only after synthesis finishes. For long course scripts, this may take a few seconds per segment, but it ensures you receive a stable file ready for your LMS.
No SSML support
We do not support Speech Synthesis Markup Language (SSML). You cannot control pronunciation, pauses, or emphasis via XML tags. Simply pass plain text, and the engine handles natural pacing automatically.
No custom cloning
SpeakFlow does not offer voice cloning or custom voice design. You choose from our eight licensed presets.

Contact and support
Support for SpeakFlow is handled entirely through email. We keep our team small and independent to maintain focus on the API’s reliability and clear documentation for no-code creators. When you reach out, you will speak directly with the team managing the service, without automated filters or tiered support levels.
We do not offer a phone number, live chat, or SLA. This approach allows us to provide detailed, written responses that you can reference later when integrating the TTS API into your LMS workflow. Our email support is the single channel for all inquiries, from billing questions to technical troubleshooting.
Email support only
All support requests are managed via email. This ensures that every query receives a thorough, documented response suitable for technical review. You can expect clear explanations regarding character usage, voice selection, or API integration steps.
No phone number
We do not maintain a phone line. Since our audience consists of developers and no-code users who often prefer asynchronous communication, email allows for better tracking of issues and solutions without the need for real-time availability.
No live chat
There is no live chat widget on our site. This reduces overhead and keeps our focus on building a stable API. You can send your question via email and receive a comprehensive answer at your convenience.
Not affiliated with
SpeakFlow is an independent storefront for a cloud text-to-speech API. We operate separately from the major voice synthesis providers often cited in industry comparisons. Our platform, pricing, and infrastructure are distinct, ensuring no implied endorsement or partnership with external brands.
OpenAI
We are not affiliated with OpenAI. While our API endpoint and request body structure mimic the OpenAI speech endpoint for ease of use, our underlying engine, voices, and billing are entirely separate. Using the OpenAI SDK with our base URL does not connect you to OpenAI’s services.
ElevenLabs
SpeakFlow is independent of ElevenLabs. We do not use their voice models, infrastructure, or brand identity. Our eight voice presets are based on licensed recordings from LibriTTS-R and LibriVox, distinct from ElevenLabs’ proprietary synthesis technology.
Other brands
We are not connected to Google, Amazon, Microsoft, or any other tech giant mentioned in TTS comparisons. Our team is small, focused, and directly manages the API infrastructure. Any mention of other brands on this site is strictly for factual comparison purposes.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This approach avoids the complexity of custom voice cloning while providing high-quality, consistent synthetic speech.
23 languages
Any voice speaks any of these languages.
