Frequently asked questions
What is AI voice text to speech?
Text-to-speech (TTS) converts written text into audio files via a cloud API. You send text, and receive an audio file. Our engine uses licensed recordings from LibriTTS-R (from LibriVox public-domain audiobook readings), ensuring high-quality synthetic speech without requiring complex infrastructure or hardware on your end.
How does the text-to-speech API work?
Send a POST request to https://api.playf44.com/v1/audio/speech with your text, voice, and format. Use standard JSON bodies compatible with OpenAI SDKs. Authenticate with a Bearer token. The API returns the audio file directly, allowing seamless integration into your existing workflows and content pipelines.
Which voices are available for content creation?
We offer eight presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). Each voice has a distinct tone, from warm narration to energetic promo. All voices support all 23 languages, allowing flexible casting for diverse blog and podcast content.
Can I use the generated audio for my blog?
Yes. The API generates audio files you can download and use. Each file contains an inaudible watermark marking it as synthetic. Input text is not used for training, and generated audio is returned in the response without being stored, giving you full control over your assets.
What languages does the TTS engine support?
We support 23 languages including English, Spanish, German, French, Japanese, and Hindi. Any voice can speak any supported language. If the language field is omitted, the system guesses from the script, defaulting to English for Latin text. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
How much does it cost to generate speech?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free with full refunds. There are no monthly plans, seats, or minimum spends. You pay only for what you generate via your balance.
Is there a free trial available?
Yes. Signing in with Google provides $0.50 of credit, valid for 7 days, covering about 50,000 characters. Accounts created with email and password start without trial credit. This allows you to test the API quality and integration before committing to a top-up via USDT.
Do I need technical skills to use the API?
Basic technical skills help, but the API is designed for ease of use. It uses standard JSON requests compatible with OpenAI SDKs. You can use the provided curl examples or any HTTP client. No custom SDK is required, making it accessible for freelancers and developers alike.
How are long texts handled in requests?
Each request supports up to 4096 characters. For longer texts, split the content into parts of up to 4096 characters and join the resulting audio files. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time for long texts.
Is the audio watermarked?
Yes. Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify the origin of the audio without affecting the listening experience. The watermark is embedded directly into the file format, whether you choose mp3, wav, opus, flac, or pcm.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful requests. This ensures you only pay for successfully generated audio. You can retry the request or adjust parameters like speed or voice to resolve any issues with the input text.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum amount is $5. Credits are automatically added to your balance within minutes after the transfer. We do not accept cards, PayPal, or subscriptions. Your balance does not expire, allowing flexible usage over time.
Can I clone my own voice?
No. We do not offer custom voice cloning for customers. You cannot upload your own voice or design custom voices. The eight presets are based on licensed recordings. If you need a specific voice, you must choose from the available options like Aria, Felix, or Atlas.
Is there an SLA guarantee for uptime?
No. We do not provide an SLA, uptime guarantee, or enterprise contracts. Requests are processed one after another, so under load, a request may wait in a queue. Typical speed is roughly real-time, but performance may vary based on server load. Support is by email only.
First request
curl
curl https://api.playf44.com/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3Turn Blog Posts into Audio
Transform written blog posts into accessible audio assets with a simple API call. By converting text to speech, you allow readers to consume your content hands-free, making your site inclusive for those with visual impairments or reading difficulties.
Accessibility for readers
Enable auditory consumption of your articles directly from the browser. This removes barriers for users who prefer listening over reading, ensuring your content reaches a wider audience without requiring complex plugins or dedicated apps.
Multi-task listening
Allow your audience to engage with your posts while commuting, cooking, or working out. Audio integration turns passive reading time into productive listening time, increasing engagement for freelancers managing multiple projects.
Content repurposing
Extend the lifespan of your written work by generating audio versions for podcasts or social media clips. Each request returns an audio file that can be downloaded and reused across your editorial calendar.
8 Distinct Voice Presets
The API provides eight distinct voice presets, each crafted from licensed LibriTTS-R recordings and public-domain audiobook readings. These voices offer consistent, high-quality synthetic speech suitable for various content formats, from casual blog reads to structured instructional guides.
Warm narrators like Aria
Aria delivers a warm, clear narration style ideal for storytelling or blog intros. Nova offers a bright, upbeat tone for engaging content, while Luna provides a soft voice perfect for intimate storytelling. Sage brings a calm, instructional clarity to educational materials.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
Energetic promos with Felix
Felix injects energy into promotional content, making him ideal for ads or dynamic updates. Milo offers a friendly, conversational tone for casual updates, while Atlas provides a neutral, news-like delivery for straightforward reporting.
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
Deep documentaries with Orion
Orion features a deep voice suited for documentary-style content or serious narratives. All eight voices support 23 languages, allowing you to maintain consistent audio branding across global content without needing multiple voice actors.
- Orion: Deep, documentary
- Supports 23 languages
- Consistent audio branding

23 Languages Supported
BlogSpeak’s text-to-speech API supports 23 languages, enabling freelancers to localize blog posts and podcast scripts for global audiences without hiring multiple voice actors. The system accepts ISO language codes to ensure precise delivery.
Global reach for content
You can generate audio in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Each voice preset is capable of speaking all supported languages natively.
Latin script language guessing
If you do not specify a language, the API guesses the language based on the script. For Latin-script text, it defaults to English. This works well for English content but may misinterpret other Latin-based languages.
Explicit language setting
For non-English Latin-script text, you should explicitly set the language field in your request. This prevents misidentification and ensures the correct voice accent and pronunciation. Unsupported languages include Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali.
Simple API Integration
Integrate BlogSpeak’s TTS API into your WordPress workflow or freelance projects without learning a new system. Our endpoint mirrors the familiar OpenAI speech structure, allowing you to use existing SDKs or simple HTTP calls.
Generate audio directly from your blog content with minimal code. The API handles the heavy lifting, returning ready-to-use audio files that you can embed in posts or export for podcast episodes.
OpenAI SDK compatible
Use the official OpenAI SDK by simply changing the base_url to https://api.playf44.com/v1. This allows you to leverage familiar libraries while accessing our specific voice models and pricing structure without rewriting your integration logic.
- Works with standard OpenAI client libraries
- Just update the
base_urlconfiguration - No custom SDK required
JSON request body
Send a standard JSON payload with your text, voice selection, and desired format. The API accepts up to 4096 characters per request, handling all synthesis parameters like speed and language in a single, clean structure.
cURL quick start
Test the API immediately using a cURL command. Authenticate with your Bearer token and receive an audio file in seconds. This method is ideal for quick validation or scripting directly into your deployment pipeline.
Transparent Pricing
BlogSpeak charges $10 per million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, ensuring you only pay for successful audio generation.
$10 per million characters
Pricing is straightforward: $10 per million characters ($0.01 per 1,000). This flat rate applies regardless of voice or format. You can estimate costs easily; for example, a 4,000-character blog post costs $0.04.
- Spaces and punctuation count as characters.
- Failed requests are free and refunded in full.
No monthly fees
There are no monthly plans, seats, or minimum spend requirements. You pay only for what you use. Unused credit does not expire, allowing you to top up whenever convenient.
USDT payments only
We accept USDT on the TRON network (TRC-20) for top-ups. The minimum deposit is $5, and credits are added automatically within minutes. We do not process cards, PayPal, or invoices with VAT.
- USDT on TRON (TRC-20) only.
- Minimum top-up: $5.

Reliable Infrastructure
BlogSpeak’s infrastructure is engineered for consistent delivery without complex setup. Requests are processed sequentially, ensuring stability even during peak usage times.
The system handles volume limits and text length automatically, so you can focus on content creation rather than monitoring server health.
60 requests per minute
Each API key supports up to 60 requests per minute, allowing steady generation for blog updates or podcast episodes. Before any top-up, the limit is 10 requests per minute.
Under load, requests are queued and processed one after another. Longer texts may take slightly longer due to this sequential processing, but delivery remains reliable.
- Standard limit: 60 requests/minute per key
- Initial limit: 10 requests/minute before top-up
- Sequential processing ensures stability
Auto-split long texts
Input text is split into parts of up to 4096 characters and joined into audio files.
This eliminates the need for manual chunking in your workflow, ensuring seamless audio for articles that exceed the character limit.
Inaudible watermarks
Every generated audio file carries an inaudible watermark that marks it as synthetic speech. This helps identify AI-generated content without affecting listening quality.
Privacy First
BlogSpeak respects your content’s ownership by using input text solely to generate the audio file, ensuring your words are never used for training models. Generated audio is returned directly in the response and is not stored on our servers, keeping your creative assets yours.
No training on input text
Unlike many consumer-grade TTS services, we do not ingest your input text into our training datasets. Your blog posts, scripts, and articles are processed only for the immediate purpose of synthesis, preserving the exclusivity of your written work.
No audio storage
The synthesized audio file is delivered to your client or application via the API response and is not retained on our infrastructure. Once the transmission is complete, the audio file itself is not stored, minimizing data exposure and simplifying your compliance obligations.
Metadata for billing only
We retain minimal request metadata—specifically timestamp, character count, and status—strictly to verify usage and process your billing accurately. This data is not used for analytics, profiling, or training and is kept only as long as necessary for accounting and dispute resolution.
Support for Creators
When you need help, you get direct assistance when you need it, backed by clear, honest documentation that explains exactly what the API does—and what it doesn't. We skip the complex support hierarchies and live chat queues that often delay responses. Instead, we provide straightforward email support tailored for freelancers who value transparency over performative immediacy.
Email support only
Our support team handles every query via email, ensuring you receive thoughtful, detailed answers without the noise of live chat windows or automated bots. This approach allows us to maintain a high level of technical accuracy for integration questions.
- No tiered support levels
- Direct access to technical details
No live chat delays
You won’t wait in a queue for a generic agent. By removing live chat, we eliminate the common frustration of being put on hold or receiving scripted responses. You receive a comprehensive answer when our team is ready to address your specific context.
Clear documentation
Our documentation is written for creators, not just engineers. It clearly outlines limitations, such as the lack of SSML or voice cloning, so you know exactly what to expect before you start building. This honesty saves time during development and integration.
- Honest feature lists
- Concrete examples for freelancers

Get Started Today
Start testing immediately with a free trial when you sign up using your Google account. This gives you $0.50 in credit, enough for roughly 50,000 characters, valid for seven days. It is the fastest way to verify voice quality and latency for your specific blog content.
Google sign-in trial
Click the Google sign-in button on the registration page to create your account. The trial credit is applied instantly, allowing you to make your first API calls without entering payment details. This trial is available only for accounts created via Google sign-in.
Email account setup
If you prefer a standard email and password setup, you can register directly on the get-api-key/ page. Unlike Google sign-up, these accounts do not receive the initial trial credit. This method is ideal for freelancers who want a clean, separate credential set for their production environment.
Instant API key
Once registered, your API key appears immediately on the dashboard. You can start sending POST requests to the speech endpoint right away. If you need to rotate credentials for security, you can issue a new key at any time, and the old one stops instantly.
- One active key per account
- Issue new keys anytime
- Old key stops immediately
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.
