Frequently asked questions
What is a Spanish text-to-speech API?
It is a cloud service where you send text via a POST request and receive an audio file. The endpoint is https://api.playsc8.com/v1/audio/speech. You can use standard HTTP or the OpenAI SDK by changing the base URL. It converts written Spanish into natural-sounding speech for accessible reading experiences without requiring complex infrastructure.
How does this API help with dyslexia?
It delivers clear, natural audio for reading, which supports users with dyslexia by providing an alternative to text. The API offers voices like Luna for soft storytelling or Sage for calm instruction. By converting text to audio, it reduces the cognitive load of decoding written words, making content more accessible and easier to consume.
Can the API read long texts?
Yes, but you must split texts into parts of up to 4096 characters per request. You then join the resulting audio files. This ensures each request stays within limits while allowing you to process documents longer than the single-request character cap. The API handles each segment sequentially to produce the final audio.
Which voices support Spanish?
All eight voices support Spanish: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. Each voice has a distinct tone, from warm narration to energetic promo. Since any voice can speak any supported language, you can choose the style that best fits your accessibility needs without being limited to a specific voice for Spanish.
Does the API support other languages?
Yes, it supports 23 languages including Arabic, Chinese, French, German, and Japanese. Any voice can speak any of these languages. If you do not set the language, it guesses from the script, defaulting to English for Latin text. For non-English Latin text, you should explicitly set the language parameter for accuracy.
How is the pricing calculated?
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 charges returned in full. There are no monthly plans, seats, or minimum spends. You pay only for the characters you successfully process, making it cost-effective for variable usage.
Is there a free trial?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without trial credit. This allows you to test the API’s quality and integration before committing to a top-up. The balance does not expire once funded.
Can I adjust the speaking speed?
Yes, you can set the speed between 0.25 and 4.0. This allows you to slow down audio for better comprehension or speed it up for quick reviews. The speed parameter is part of the JSON request body. Adjusting speed helps tailor the listening experience to different accessibility needs or user preferences.
What audio formats are supported?
The API supports mp3, wav, opus, flac, and pcm formats. You specify the desired format in the response_format field of your request. These formats cover various use cases, from web playback to high-quality archival. The generated audio is returned directly in the response, ready for immediate use in your application.
Is my input text stored?
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, such as time and characters, is kept for billing purposes. This ensures your content remains private and is not repurposed for model improvement.
How fast is the synthesis?
Typical speed is roughly real time, generating about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. This ensures consistent quality.
Can I use the OpenAI SDK?
Yes, the API uses the same request shape as the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.playsc8.com/v1 and using your site’s key. This allows for easy integration if your team is already familiar with OpenAI’s client libraries and workflow.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successful audio generation. You can retry the request or adjust parameters like text length or voice. The system handles failures gracefully without affecting your balance for those specific attempts.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum amount is $5, and credits are automatically added within minutes after transfer. There are no cards, PayPal, or invoices. Balance does not expire. This method provides a direct, low-friction way to fund your account for ongoing API usage.
First request
curl
curl https://api.playsc8.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.mp3How the Spanish Text-to-Speech API Works
ClearRead turns Spanish text into natural audio through a simple API call. Send your content via JSON, and receive a clean audio file ready for your accessibility features. It’s designed to integrate smoothly into reading aids and language learning tools without adding complexity.
The process is straightforward: input text, select a voice, and get audio back. This reliability helps product teams deliver consistent listening experiences for users with dyslexia or those practicing Spanish, ensuring the infrastructure stays out of the way of the reading experience.
Send text, receive audio
You send a POST request to our endpoint with your Spanish text and desired settings. The API processes the input and returns a standard audio file. No complex setup or custom SDKs are needed; you can use existing HTTP clients or the OpenAI SDK with a simple base URL change.
This direct approach keeps your code clean. You can set the language to Spanish to ensure accurate pronunciation, then receive the audio file. It’s a seamless loop that fits into any web or mobile application.
- POST to /v1/audio/speech
- JSON input with text and voice
- Returns standard audio formats like mp3 or wav
Instant synthesis via API
Synthesis is fast and predictable. Short phrases generate in a few seconds, while longer texts process at roughly real-time speed (about 25 characters per second). This consistency helps maintain a smooth user experience, even during peak usage.
Requests are processed sequentially, so under heavy load, there may be a brief queue. However, for typical product team workloads, the response time is quick enough to keep readers engaged without noticeable delay.
Support for long-form content
For longer articles or chapters, split your text into chunks of up to 4,096 characters. Generate audio for each part and join the files. This method ensures high-quality audio without hitting character limits, making it ideal for books, podcasts, or educational content.
This approach gives you full control over the pacing and structure of your audio. You can manage the segments to match your UI’s navigation or chapter markers, providing a professional listening experience for your users.
Voices Optimized for Clarity
ClearRead uses licensed recordings from LibriTTS-R and LibriVox to deliver clear, natural audio for accessible reading. We selected three voices that prioritize clarity and ease of listening, ensuring your users can focus on the content without distraction.
Aria: warm narrator
Aria provides a warm, clear narration style. Her tone is ideal for educational content or longer texts where a steady, engaging presence helps maintain reader focus.
Nova: bright and clear
Nova brings a bright, upbeat energy to your audio output. Her clear articulation makes her suitable for quick updates or dynamic reading experiences that need a lively touch.
Luna: soft storytelling
Luna offers a soft, storytelling voice. Her gentle tone is perfect for immersive narratives or calming reading sessions, helping users relax while they listen.
Support for Dyslexia and Reading Aid
ClearRead’s TTS API helps teams build reading aids that reduce cognitive load for users with dyslexia. By delivering consistent, high-quality audio, we remove the friction of decoding complex text, allowing users to focus on comprehension rather than struggling with visual noise.
The engine prioritizes clarity over dramatic flair, ensuring every word is distinct. This steady delivery helps maintain flow, making long-form content like articles or books easier to process without the fatigue that often comes with rapid or inconsistent speech.
Clear pronunciation
The voices are designed for clear articulation. Each character is delivered with distinct enunciation, which helps users distinguish between similar phonemes. This clarity is critical for readers who need extra support to separate words and understand syntax without visual cues.
The API handles complex sentence structures smoothly, ensuring that pauses and intonation follow natural speech patterns. This reduces the mental effort required to parse meaning, making the audio feel like a helpful guide rather than a robotic reader.
- Distinct articulation for complex phonemes
- Natural intonation patterns
- Reduced cognitive load
Adjustable speed
Users can adjust the playback speed from 0.25x to 4.0x, allowing them to find the perfect pace for their processing speed. Slower speeds help with detailed decoding, while faster speeds support quick review. This flexibility ensures the audio matches the user’s comfort zone without rushing or dragging.
The API maintains clarity even at higher speeds, preventing the speech from becoming slurred or indistinct. This feature is particularly useful for language learners who are building their listening skills or users who need to skim content quickly.
- Speed range: 0.25x to 4.0x
- Maintains clarity at high speeds
- Customizable to user preference
Consistent rhythm
The TTS engine delivers a steady, predictable rhythm that helps users anticipate the flow of speech. This consistency reduces the anxiety of unexpected pauses or erratic pacing, which can disrupt concentration. Users can rely on a uniform delivery style that supports sustained listening sessions.
By avoiding dramatic shifts in tone or volume, the audio remains engaging without being distracting. This steady cadence is ideal for educational materials, audiobooks, and accessibility features where predictability enhances understanding and retention.
- Steady cadence
- Predictable pauses
- Uniform tone delivery
Language Learning Features
Language learning benefits from clear, consistent audio that models natural speech patterns without requiring complex infrastructure. Our API provides stable pronunciation and rhythm, helping learners build listening skills and confidence through repeated, accurate exposure.
Spanish voice presets
Choose from eight distinct voices, including female options like Aria and Luna, or male options like Felix and Milo.
Native-like intonation
Synthesized speech uses natural inflection patterns, helping users grasp the musicality of the language.
Controlled pacing
Adjust speed from 0.25x to 4.0x to match your learning level. Slower rates improve clarity for complex words, while faster speeds simulate natural conversation. This flexibility supports both beginners and advanced learners.
Accessibility Standards Compliance
ClearRead delivers consistent, high-quality audio that aligns with WCAG guidelines for accessible reading experiences. Our API generates clear, natural-sounding speech that supports accessibility standards, ensuring reliable output for assistive technologies without unpredictable variations.
WCAG-aligned audio output
We generate clear, natural-sounding speech that supports accessibility standards. The consistent voice presets provide predictable audio patterns, helping users with dyslexia or reading difficulties focus on content rather than decoding inconsistent pronunciation.
Predictable response times
Requests are processed sequentially, taking roughly real-time duration (about 25 characters per second). While short phrases take a few seconds, longer texts scale linearly. Under load, requests may queue briefly, but you get reliable timing for planning your user interface.
Standard audio formats
We return standard formats like MP3, WAV, Opus, FLAC, and PCM. These widely supported codecs integrate seamlessly with existing web players and accessibility tools, avoiding the need for custom decoding infrastructure in your product.
Integration for Product Teams
Product teams can integrate our Spanish TTS API using the official OpenAI SDK by simply updating the base_url to https://api.playsc8.com/v1. This allows you to use familiar client libraries without learning a new protocol.
OpenAI SDK compatible
Use the standard OpenAI Python or JavaScript SDKs. Change the base_url to point to our API endpoint and pass your tts-... key. This maintains your existing code structure while accessing our synthesis engine.
Simple JSON requests
Send a POST request to /v1/audio/speech with a JSON body. Include model, input, voice, and response_format. The API returns the audio file directly, ready for playback in your app.
- Supports
mp3,wav,opus,flac, andpcmformats. - Set
speedbetween 0.25 and 4.0 for customizable pacing. - Optional
languagefield ensures correct pronunciation for non-English Latin text.
Fast deployment
Get your API key in minutes after signing up. Start sending text immediately with the provided cURL example. No complex infrastructure setup or long onboarding processes are required.
Transparent Pricing Model
ClearRead charges $0.01 per 1,000 characters, making it easy to budget for your accessibility features. Every character, including spaces and punctuation, counts toward the total. You only pay for successful synthesis; if a request fails, the charge is returned in full.
Pay per character
The cost is $10 per 1 million characters. This flat rate applies to both tts-1 and tts-1-hd models, so you can choose the quality that fits your needs without worrying about tiered pricing structures.
No hidden fees
There are no monthly plans, seats, or minimum spend requirements. We do not charge for VAT or invoices. You can top up with USDT on the TRON network whenever you need more balance, and funds never expire.
Free trial available
Sign up with Google to receive $0.50 in credit, enough for about 50,000 characters. This trial lasts for 7 days, giving your team time to test the Spanish voices and integration workflow before committing to a top-up.
Data Privacy and Usage
When you send text to the ClearRead API, that input is used strictly to generate the audio file you receive. We do not use your text data to train our underlying models or improve the engine over time. Your content remains yours, ensuring that proprietary stories, educational materials, or customer data stay private.
Text not used for training
The text you submit via the API is processed solely for the purpose of creating the requested audio output. Unlike many consumer-grade services, ClearRead does not ingest your input text into our training datasets. This means your specific phrasing, narratives, or data points remain distinct from the core model improvements.
No audio storage
Generated audio files are returned directly in the API response and are not stored on our servers for later access or analysis. Once the audio is delivered to your application, it lives in your infrastructure. We retain no copies of the spoken content, giving you full control over your audio assets.
Minimal metadata kept
We keep only the necessary metadata for billing and service reliability. This includes the timestamp, character count, and request status. This limited data is used exclusively to calculate costs and manage your account balance, ensuring transparency without retaining your actual content or audio files.
Get Started with Spanish Text-to-Speech
Start by creating a free account on our platform. You can sign up instantly using your Google account or by setting up a standard email and password. This gives you immediate access to your dashboard and trial credit.
Sign up for free
Signing up takes just a few seconds. If you use Google, you receive $0.50 in trial credit (about 50,000 characters) valid for 7 days. Email-based accounts start without trial credit but are ready for top-ups immediately.
Get your API key
Once registered, visit the /get-api-key/ page to view your unique authentication key. This single key controls all your API requests. You can generate a new key at any time, which immediately invalidates the old one for security.
First request in minutes
With your key ready, you can make your first API call immediately. Use the OpenAI SDK by pointing it to https://api.playsc8.com/v1 or send a simple POST request to /v1/audio/speech. Your first synthesis will return an audio file in seconds.
- Rate limit: 60 requests per minute
- Supports 23 languages including Spanish
- Formats: mp3, wav, opus, flac, pcm
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Python documentation
- LibriTTS-R paper (arXiv 2305.18802)
- LibriVox public-domain audiobooks
- ISO 639 language codes
- OpenAI API reference: create speech
- LibriTTS-R corpus (OpenSLR 141)
- W3C WAI: making audio and video accessible
- openai-node on GitHub
- Node.js documentation
- IETF RFC 7845: Ogg Opus
- Tether (USDT)