Frequently asked questions
What is the ReadAloud Freelance API?
It is a cloud text-to-speech API where you send text and receive an audio file. The endpoint matches the OpenAI speech format, so official OpenAI SDKs work by changing the base URL. You can generate speech in 23 languages using simple HTTP requests or standard libraries without managing infrastructure.
How do I integrate TTS into a WordPress blog?
Use the standard HTTP endpoint or OpenAI SDK by setting the base URL to https://api.ub150.net/v1. Send your blog text via POST request with your API key. Receive the audio file and embed it in your WordPress posts. There is no official WordPress plugin, so you handle integration via code or custom scripts.
Which voices are available for freelancers?
Eight presets are available: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These include warm narrators, upbeat voices, and neutral news styles. All voices can speak any of the 23 supported languages. Each generated file carries an inaudible watermark marking it as synthetic speech.
Can I use this API for client projects?
Yes, the API is built for freelancers turning text into audio for clients. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored, making it suitable for delivering clean audio files to your clients.
How many languages are supported?
The API supports 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. Vietnamese and Indonesian are not supported.
What audio formats can I generate?
You can generate audio in mp3, wav, opus, flac, or pcm formats. Specify the desired format in the response_format field of your POST request. These formats cover most blogging and accessibility needs. The API returns the audio file directly in the response.
Is there a free trial for new users?
Yes, signing in with Google gives you $0.50 of credit, valid for 7 days. This covers about 50,000 characters. Accounts created with email and password start without trial credit. You can top up later using USDT on the TRON network.
How does the character billing work?
Billing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full. There are no monthly plans or minimum spends. Your balance does not expire.
Do I need technical skills to use this API?
Basic technical skills are needed to make HTTP requests or use the OpenAI SDK. The endpoint matches the OpenAI speech format, so existing code may work with a base URL change. You manage your own API keys and request structures. No SDK is provided, but standard libraries work. There is no official SDK of our own.
Can I adjust the speech speed?
Yes. Use the speed field in your request body to set values between 0.25 and 4.0. This lets you adjust speech pace to fit your project needs. The default speed is 1.0. Simply include this parameter in your POST request to https://api.ub150.net/v1/audio/speech to control the generation speed.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. You can retry the request or adjust parameters like text length or voice. The API processes requests sequentially, so high load might cause delays, but failures are refunded. Rate limit is 60 requests per minute per key.
Is my text data used for training?
No, input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Request metadata like time and status is kept for billing purposes only. Your content remains private.
How do I get support for my account?
Support is available by email only. There is no live chat, phone number, or SLA. You can contact support for account or billing issues. Response times are not guaranteed. Check the /contact/ page for the support email address.
Does the API handle long articles automatically?
No, the API handles up to 4096 characters per request. For longer texts, you must split the text into parts, generate audio for each, and join the files. The API does not automatically split and join audio. You handle this logic in your integration.
First request
curl
curl https://api.ub150.net/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.mp3Voice Content for Your Clients
Transform written content into engaging audio for your clients. Whether they need background narration for blog posts or voiceovers for marketing materials, our API handles the heavy lifting so you can focus on strategy and delivery.
Generate high-quality speech in 23 languages without managing infrastructure. Your clients get professional, natural-sounding audio files ready for immediate use in their websites, apps, or presentations.
Blog Post Audio
Turn long-form blog posts into listenable content. Clients can consume articles during commutes or while working, increasing engagement and time on site. Send up to 4096 characters per request and receive an audio file ready for embedding.
Support multiple languages natively. If a client writes in French, German, or Japanese, the API handles the synthesis automatically, ensuring consistent quality across their global audience. For non-English Latin-script text, you should set the language parameter to ensure accurate pronunciation.
- Ideal for audio versions of blog posts
- Supports 23 languages including English, Spanish, and Japanese
- Easy embedding with standard audio tags
Client Deliverables
Deliver professional voiceovers for e-learning modules, audiobooks, or promotional videos. Choose from 8 distinct voice presets to match the tone of each project, from calm storytelling to energetic promos.
Ensure consistency across all client assets. Every generated file includes an inaudible watermark marking it as synthetic speech, providing transparency without affecting the listening experience.
- 8 professional voice presets
- Consistent tone across projects
- Inaudible synthetic watermark included
Technical Simplicity
Freelancers value tools that fit existing workflows. Our API mirrors the OpenAI speech endpoint structure, allowing you to switch providers or integrate quickly without rewriting logic. You simply adjust the base URL and use your API key with standard OpenAI SDKs.
Under the hood, it is a straightforward REST API. Send a JSON payload with your text and voice preference, and receive an audio file. No complex streaming protocols or custom SDKs to learn. There is no streaming support. Just clean, reliable requests that return MP3, WAV, OPUS, FLAC, or PCM formats.
OpenAI SDK Compatible
Use the official OpenAI SDKs by changing the base_url to https://api.ub150.net/v1. This means your existing Python, Node.js, or Go code works with minimal changes. Just swap the endpoint and inject your tts-... API key.
- Drop-in replacement for OpenAI's speech endpoint
- Works with official OpenAI SDKs (Python, Node.js, etc.)
- No custom client library required
Simple JSON API
The request body is standard JSON. Provide model, input, voice, and response_format. If you need speed control, add the speed parameter. The endpoint returns the audio file directly, ready to save or stream to your client.
Authentication is handled via a simple Bearer token in the header. One key per account, issued instantly. If you need to rotate keys for security, a new key invalidates the old one immediately, with no downtime.
- POST to
/v1/audio/speech - JSON body with standard fields
- Bearer token authentication
Voice Selection
Choose from eight distinct voice presets designed for different content styles. Whether you need a warm narrator for long-form blog posts or an energetic tone for promotional clips, our library covers the spectrum of professional audio needs.
8 Professional Presets
Each voice is based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox, ensuring high-quality, natural-sounding speech. You can select specific voices like Aria for clear narration, Felix for upbeat promos, or Orion for deep, documentary-style audio.
- Aria: Warm, clear narrator
- Felix: Energetic, promo
- Orion: Deep, documentary
- Sage: Calm, instructional
Gender Variety
Our selection includes both female and male voices, giving you the flexibility to match the tone of your client’s brand. Mix and match voices across projects to keep content fresh and engaging for your audience.
Language Support
Generate clear, natural audio in 23 languages, from Arabic and Swahili to Japanese and Portuguese. Every voice supports all listed languages, ensuring consistent quality whether you’re localizing a blog post or creating accessible content for a global audience.
You don’t need to guess the language. The API automatically detects the script from your input text. If you send Latin characters, it defaults to English. For other Latin-script languages, simply set the language parameter to ensure accurate pronunciation.
23 Languages Supported
Our API handles 23 distinct languages, covering major global markets and specific regional needs. You can produce high-quality speech 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.
This wide range allows freelancers to serve diverse clients without managing multiple voice models or language-specific infrastructure. Each voice maintains its unique character across all supported languages.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German
- Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay
- Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Auto-Detection
The API automatically infers the language from the script of your input text. Latin text defaults to English. For non-English Latin-script text, you should explicitly set the language field to avoid defaulting to English. This ensures precise pronunciation for languages that share similar character sets.
This feature simplifies your workflow, reducing the need for manual language configuration while maintaining high accuracy in voice synthesis.
Audio Formats
Generate audio in the formats your workflow requires. MP3 offers efficient compression for web delivery, while WAV provides uncompressed quality for professional editing. Choose the right balance between file size and fidelity for your specific client needs.
MP3 and WAV
Use MP3 for lightweight blog audio or quick previews. Opt for WAV when you need pristine, uncompressed audio for post-production or high-end client deliverables. Both formats are directly returned in the API response for immediate use.
Lossless Options
For archival quality or specialized processing, select FLAC, OPUS, or PCM. FLAC provides lossless compression, preserving every detail of the synthesis. OPUS offers efficient high-quality encoding. PCM is available for raw data needs. All formats support speeds from 0.25x to 4.0x.
- FLAC: Lossless compression for perfect quality
- OPUS: Efficient high-quality encoding
- PCM: Raw uncompressed data
- WAV: Standard uncompressed audio

Pricing Model
Stop paying for idle capacity. You only pay for what you actually generate: $0.01 per 1,000 characters, which covers spaces and punctuation. This straightforward model means your costs scale exactly with your client workload, making budgeting for diverse blog content predictable and fair.
Pay Per Character
The rate is $10 per 1 million characters. Failed requests are free, so you never pay for errors. A free trial gives you $0.50 credit (about 50,000 characters) valid for 7 days when you sign in with Google.
- $0.01 per 1,000 characters
- Failed requests are free
- $0.50 free trial credit for Google sign-ups
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. Top-ups are made via USDT on the TRON network (TRC-20) with a $5 minimum. Your balance does not expire, so you can pay as needed without recurring commitments.
Integration
Freelancers often need to embed audio directly into WordPress posts without complex plugins or heavy page loads. With our API, you generate the audio file via a simple script and upload it as a standard media asset, keeping your theme light and your workflow flexible.
WordPress Ready
You can automate the process by writing a custom function that calls the API when you publish a post. This ensures every blog post gets consistent, high-quality narration without manual uploads or waiting for support.
- Works with any theme or page builder
- No required WordPress plugin. There is no official WordPress plugin.
- Standard audio player compatibility
API First
The core is a standard JSON endpoint compatible with the OpenAI SDK. You simply change the base URL to https://api.ub150.net/v1 and use your key. This lets you build custom integrations for client portals, mobile apps, or internal tools with minimal code.
Quality
Synthesized speech uses licensed recordings from LibriVox, ensuring a natural, human-like listening experience for your blog readers and clients. Each generated file includes an inaudible watermark to clearly mark the content as synthetic speech, maintaining transparency without disrupting the audio flow.
The engine delivers consistent tone across all 23 supported languages, avoiding the robotic cadence common in older TTS systems. With speed control from 0.25x to 4.0x, you can fine-tune the pace to match your specific accessibility or storytelling needs.
Natural Speech
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings. This foundation provides a warm, clear, and realistic listening experience that engages audiences without sounding overly mechanical.
- Eight distinct voice presets for varied content styles
- Inaudible watermark marks files as synthetic speech
- No robotic pauses or unnatural intonation. No emotion tags are supported.
Consistent Tone
Every generation maintains a steady emotional baseline, ensuring your long-form content sounds professional from start to finish. Whether you are creating a documentary-style narration or a quick blog update, the voice remains reliable and recognizable.
- Uniform quality across short phrases and long texts. Short phrases may take a few seconds to generate.
- Adjustable speed (0.25–4.0) for precise control
- No unexpected emotion shifts or tone changes
Accessibility
Turn static blog posts into accessible audio for users who prefer listening. With support for 23 languages, you can generate speech that serves a global audience without hiring multiple voice actors.
The API returns clean audio files that integrate seamlessly into your content workflow, ensuring your readers have a choice between reading and listening.
Screen Reader Alternative
Many users find long articles tedious to read on mobile devices. By adding audio versions via our TTS API, you provide a convenient alternative to standard screen readers, reducing bounce rates and increasing engagement for on-the-go listeners.
- Supports 23 languages for diverse audiences
- No infrastructure management required
- Fast generation for quick turnaround
Inclusive Content
Accessibility is not just a feature; it is a standard. Our natural-sounding voices ensure that your content is inclusive for users with visual impairments or reading difficulties, complying with modern web standards effortlessly.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. For content creators working with diverse audiences, language support is critical.
23 languages
Any voice speaks any of these languages.
