Frequently asked questions
Who runs BlogSpeak?
BlogSpeak is an independent storefront for the BlogSpeak text-to-speech API. We are not affiliated with OpenAI, ElevenLabs, or other major brands. Our team focuses on providing reliable API access and editorial context for freelancers and content creators who need to turn written words into audio assets without complex infrastructure.
Where do the voices come from?
Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0), which includes public-domain audiobook readings from LibriVox. These recordings form the foundation of our synthetic speech engine, ensuring high-quality audio generation while maintaining clear attribution to the original licensed source material used in our API.
Is my text data used for training?
No. Input text is used solely to produce the audio file for your request. We do not use your submitted text for training our models. This ensures that your content remains private and is not repurposed to improve the underlying speech synthesis engine used by other customers.
Do you store generated audio?
Generated audio is returned directly in the API response and is not stored on our servers. We retain request metadata, such as timestamp, character count, and status, strictly for billing purposes. Your actual audio files are delivered to you and are not kept in our long-term storage.
How can I contact support?
Support is available via email only. We do not offer a phone number or live chat. You can reach our support team through the contact page or by emailing us directly. We aim to respond to your inquiries promptly to assist with any API or billing questions.
Is there a phone number?
No, there is no phone number for BlogSpeak. All customer support is handled via email. This allows us to maintain a direct line of communication for technical and billing issues without the overhead of a traditional call center, ensuring your queries are addressed by our dedicated team.
Are the voices licensed?
Yes, our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain readings from LibriVox. These sources provide the foundational audio data for our eight presets. We ensure that the underlying recordings meet licensing requirements so you can confidently use the generated audio for your projects.
Can I use the voices commercially?
Yes, you can use the generated audio commercially. The underlying recordings come from CC BY 4.0 and public-domain sources. Since we provide the TTS API service, you receive the audio files directly. There are no additional restrictions on commercial use beyond the standard terms of your API account and billing.
Do you have an SLA?
No, we do not offer a Service Level Agreement (SLA) or uptime guarantee. Our service is provided as-is without enterprise contracts or on-premise options. This allows us to keep pricing simple and transparent at $0.01 per 1,000 characters without the costs associated with guaranteed uptime metrics.
Is the site affiliated with OpenAI?
No, BlogSpeak is not affiliated with OpenAI. We are an independent storefront. Our API endpoint mimics the OpenAI speech endpoint structure, so you can use the official OpenAI SDK by changing the base URL. This compatibility is a convenience feature, not an endorsement or partnership with OpenAI.
What is the editorial team?
The editorial team provides context and guides freelancers on using the BlogSpeak API for blogs and podcasts. We focus on editorial content rather than just technical documentation. Our goal is to help content creators integrate text-to-speech into their workflows effectively, offering insights on voice selection and text preparation.
Do you offer refunds?
Failed requests are free, and the charge is returned in full if synthesis fails. For other cases, refunds are not explicitly guaranteed beyond failed requests. Your balance does not expire, so you can use your credit whenever you are ready. Top-ups via USDT (TRC-20) are processed automatically.
Who We Are
BlogSpeak is an editorial-driven independent storefront built for freelancers and content creators who need reliable text-to-speech without complex infrastructure. We provide the API access and editorial context to turn written words into audio assets for blogs and podcasts.
Our focus is on providing clear, specific documentation and practical workflows that fit directly into your existing publishing process. We prioritize transparency in pricing and voice options, ensuring you know exactly what you are getting.
Editorial team focus
We approach TTS as a content tool first.
Freelancer community
Designed for independent voices, our API handles the technical heavy lifting. You can split long texts, manage speed, and choose formats like MP3 or WAV without worrying about server maintenance or scaling infrastructure.
Independent storefront
We are not affiliated with major tech brands. We operate as a dedicated API provider, meaning your billing, keys, and support are handled directly by us. This independence allows us to keep pricing simple and transparent.
Voice Licensing
BlogSpeak provides a straightforward text-to-speech API designed for freelancers and content creators who need reliable audio assets without complex infrastructure. Our editorial focus ensures that the technology remains simple, transparent, and directly useful for turning written words into podcast or blog audio.
We operate as an independent storefront, offering direct API access with clear pricing and no hidden fees. This approach allows creators to integrate speech synthesis into their workflows without managing enterprise-level contracts or waiting for support tickets.
LibriTTS-R source
Our eight voice presets are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0), which includes public-domain audiobook readings from LibriVox.
CC BY 4.0 license
The underlying recordings are licensed under Creative Commons Attribution 4.0 International.
LibriVox recordings
The voice models are based on public-domain audiobook readings available on LibriVox.

Data Privacy
Your input text is used exclusively for the immediate synthesis of the requested audio file and is not retained for model training. This ensures that your proprietary blog posts, podcast scripts, or creative writing remain yours, with no secondary usage rights granted to us.
No text training
We do not ingest your submitted text into our training dataset. The input is processed solely to generate the audio output and is discarded after the request completes.
No audio storage
The generated audio is returned directly in the API response and is not stored on our servers. Once you download the file, we have no copy of your audio asset.
Billing metadata only
We retain minimal request metadata—specifically the timestamp, character count, and status—to accurately calculate your usage and apply charges. This data is used strictly for billing purposes and is not linked to the content of your text.
Honest Limitations
Our API prioritizes reliable, batch-processing audio generation over real-time interactivity. You send a request and receive a complete file; there is no WebSocket streaming or partial audio chunks. This design keeps infrastructure simple and predictable for freelancers managing blog or podcast workflows, though it means you cannot hear audio incrementally as it is being synthesized.
The engine does not yet support SSML (Speech Synthesis Markup Language). You cannot use tags to control pauses, emphasis, or pronunciation within your text. While we offer eight distinct voice presets to cover most tonal needs, precise editorial control over micro-pauses or specific word stress must be handled by editing the input text itself before sending it to the endpoint.
No streaming support
Requests are processed sequentially, meaning a burst of requests may queue behind longer generations, with a typical speed of roughly real time. You receive the final audio file via the response, not a continuous stream. This ensures stable billing and consistent quality but requires your application to handle the wait time for each 4096-character chunk.
No SSML yet
We do not currently support SSML tags for fine-grained control over speech properties. You cannot inject explicit pause durations or emphasis markers directly into the JSON body. For editorial precision, adjust the punctuation and phrasing of your input text to influence the natural rhythm of the generated audio.
No custom cloning
We do not offer custom voice cloning or the ability to upload a sample of your own voice. Our eight presets are derived from licensed LibriTTS-R recordings. If you need a unique voice, you must choose from the existing catalog of male and female presets rather than creating a custom clone.
- No uploading of personal voice samples
- No custom voice model training
- Fixed set of 8 licensed presets

Contact Information
BlogSpeak operates as an independent storefront for freelancers and content creators who prefer straightforward, asynchronous communication. We provide the API access and editorial context to turn written words into audio assets, keeping our support structure simple and transparent.
Email support only
Our support team handles all inquiries via email. This allows us to provide detailed, thoughtful responses tailored to your specific API or billing questions without the pressure of immediate availability.
No phone number
We do not offer a phone number. As a digital-first API provider, we believe email is the most reliable way to document technical details and pricing discussions for future reference.
No live chat
There is no live chat widget on our site. This ensures that every conversation receives full attention from a single support agent, reducing the back-and-forth often experienced in shared chat environments.

Mission Statement
BlogSpeak exists to bridge the gap between written content and audio consumption for independent creators. We provide a straightforward API that turns blog posts and scripts into usable audio assets without demanding complex infrastructure or deep technical expertise.
Empower creators
Our goal is to give freelancers and content producers the tools to repurpose text into audio efficiently. By removing infrastructure headaches, we let you focus on the quality of your writing and the experience of your listeners.
Transparent pricing
We charge strictly by usage: $0.01 per 1,000 characters. There are no monthly subscriptions, hidden seat fees, or minimum spend requirements. You pay only for what you generate, and failed requests are refunded automatically.
Simple technology
Our technology relies on standard OpenAI-compatible endpoints, meaning you can use familiar SDKs and workflows. We offer eight distinct voices and support for 23 languages, ensuring your audio sounds natural without requiring custom voice design or complex configuration.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Mastering WordPress unlocks endless freelance opportunities for creative bloggers seeking financial independence.
23 languages
Any voice speaks any of these languages.
