Frequently asked questions
What is speech synthesis for meditation content?
It is a cloud API that converts your written scripts into audio files. Send text via a POST request, and receive an MP3, WAV, or other format. This allows fitness and meditation creators to generate calm, natural voiceovers programmatically without recording studios, scaling production with simple code integration.
How many characters can I process at once?
Each API request accepts up to 4096 characters of input text. For longer scripts, you can split the text into smaller parts, generate audio for each segment, and join the files. This ensures consistent quality and manageable processing loads for extended guided meditation sessions.
Can I use the generated audio for commercial fitness videos?
Yes. The API generates synthetic speech files that you can use in your content. Input text is not used for training, and generated audio is not stored after delivery. You retain the rights to use the resulting audio files in your commercial fitness or meditation videos.
Which voices are best for guided meditation?
Luna offers a soft, storytelling tone ideal for meditation. Sage provides a calm, instructional voice suitable for guided exercises. Aria is a warm, clear narrator, while Orion’s deep, documentary style also works well. All eight voices support multiple languages, allowing you to choose the perfect tone.
Do I need technical skills to use the API?
Basic technical knowledge is helpful but not required. The API uses a standard JSON request structure similar to OpenAI’s speech endpoint. You can use the official OpenAI SDKs by changing the base URL. A ready curl example is provided on the dashboard to help you get started quickly.
How fast is the speech synthesis output?
Generation takes roughly real time, averaging 25 characters per second for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so under heavy load, a request might wait in a queue. Typical usage remains fast enough for most content creation workflows.
Is there a limit on how much I can generate?
There is no hard limit on total generation volume. You pay per character used, with a rate of $10 per million characters. Failed requests are free. You can top up your balance with USDT on the TRON network (TRC-20) at any time. There are no monthly plans or minimum spend requirements.
Can I change the speed of the speech synthesis?
Yes. You can adjust the speech speed between 0.25 and 4.0 using the speed parameter in your API request. This allows you to slow down voiceovers for calming meditation tracks or speed up instructional content. The default speed provides a natural, balanced pace for most use cases.
What formats are supported for audio download?
The API supports MP3, WAV, OPUS, FLAC, and PCM formats. You can specify the desired response format in your request. This flexibility allows you to choose the best balance between file size and quality for your specific fitness or meditation content distribution channels.
Do you support voice cloning for my own voice?
No, custom voice cloning is not offered. The API provides eight preset voices based on licensed recordings from LibriTTS-R and LibriVox. You cannot upload your own voice or design custom voices. Each generated file includes an inaudible watermark to identify it as synthetic speech.
Is the speech synthesis real-time or delayed?
It is not real-time streaming; you send a request and receive the full audio file. Generation takes roughly real time (25 characters per second). Requests are processed sequentially, so delays may occur under load. There is no WebSocket or partial audio streaming support.
Can I use the API for live streaming voiceovers?
The API is not designed for live streaming. It generates complete audio files after processing the request. There is no real-time partial audio or WebSocket support. For live streaming, you would need to pre-generate audio files or manage buffering, as the API returns full files upon completion.
Do you offer SSML support for pause control?
No, SSML support is not available. You cannot use SSML tags for pause control or pronunciation adjustments. The API accepts plain text input. For precise control, you can adjust the speed parameter or split your text into smaller segments to manage pacing manually.
How do I track my usage and costs?
The dashboard on /get-api-key/ displays your balance, characters left, and usage history. You can see your API key and current status. Request metadata is kept for billing, and failed requests are refunded. You can top up your balance via USDT on the TRON network.
First request
curl
curl https://api.playmk77.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.mp3Why Creators Choose Our API
MindVoice delivers consistent audio quality across thousands of characters, ensuring your meditation guides and fitness scripts sound professional every time. The API handles text splitting and joining seamlessly, so your workflow remains smooth whether you are recording a short affirmation or a full session.
With typical generation speeds of roughly 25 characters per second, you can produce content quickly, though requests are processed sequentially and may wait in a queue under load. This reliability helps you maintain a steady publishing schedule for your audience.
Consistent Voice Quality
Our eight voice presets, from Luna’s soft storytelling to Felix’s energetic promo style, are based on licensed recordings. Each file includes an inaudible watermark to identify synthetic speech, ensuring transparency for your listeners.
Fast Turnaround
Requests are processed in order, with short phrases generating in just a few seconds. Longer texts are split into parts of up to 4096 characters and joined automatically, keeping the process efficient.
Easy Integration
Use the standard OpenAI SDKs by simply changing the base URL to https://api.playmk77.com/v1. Send a JSON POST request with your key, and receive audio in seconds. No custom libraries required.
Voices for Calm and Energy
Choose from eight distinct voice presets designed to match the rhythm of your content. Whether you need a gentle guide for a yoga session or a motivating voice for a high-intensity workout, our library offers eight distinct presets to match your content style.
These voices are based on licensed recordings from LibriTTS-R and LibriVox. Each voice maintains consistent tone throughout long scripts, perfect for multi-hour meditation tracks or fitness playlists.
Soft Narrators
Aria and Luna offer warm, clear tones ideal for storytelling and relaxation. Their soft delivery helps listeners unwind during guided meditations or sleep stories.
Sage provides a calm, instructional presence that works well for mindfulness exercises, ensuring your audience stays focused and relaxed.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling voice
- Sage: Calm, instructional tone
Energetic Coaches
Felix brings high energy to promotional content or workout cues, keeping listeners engaged and motivated. Nova adds a bright, upbeat quality suitable for morning routines or active sessions.
Milos friendly, conversational style makes instructions feel personal, helping users connect with their fitness journey without feeling like they are listening to a robot.
- Felix: Energetic, promo
- Nova: Bright, upbeat
- Milo: Friendly, conversational
Neutral Guides
Atlas delivers a neutral, news-like tone perfect for clear, distraction-free instruction. Orion offers a deep, documentary-style voice that adds gravity and seriousness to your content.
These voices ensure your message is heard without emotional bias, making them ideal for educational fitness content or serious mindfulness practices.
- Atlas: Neutral, news
- Orion: Deep, documentary

Support for Global Audiences
MindVoice supports 23 languages, including English, Spanish, German, French, and Hindi, allowing you to reach a global audience without hiring multiple voice actors. Every voice can speak any of these languages, ensuring consistent quality across your entire content library.
Whether you are producing fitness routines or meditation guides, you can maintain a uniform brand voice while speaking to listeners in their native tongue. This flexibility helps you scale your content creation efficiently across different regions.
23 Languages Supported
Our API covers Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. You do not need separate accounts or integrations for each language.
Accent Variety
With eight distinct voice presets, you can choose the right tone for your specific niche. Select a calm voice like Luna for deep meditation sessions or an energetic option like Felix for high-intensity workout instructions.
Each voice offers a unique character, allowing you to match the audio precisely to the visual energy of your video content.
Cultural Nuance
Set the language code explicitly to ensure correct pronunciation. If the language is not set, it is guessed from the script (Latin text defaults to English), so for non-English Latin-script text you should set the language.
How It Works
To turn your script into audio, simply send a POST request to the speech endpoint with your text, chosen voice, and desired format. The API accepts inputs up to 4,096 characters, allowing you to process meditation instructions or fitness cues directly from your content management system.
Once processed, you receive the audio file immediately. For longer scripts, the system splits the text into manageable segments, synthesizes each part, and returns the complete audio sequence, ensuring your guided sessions flow naturally without manual intervention.
Send Text
Prepare your script, ensuring it stays within the 4,096 character limit per request. Include the desired voice preset, such as Luna for soft storytelling or Felix for energetic promos, and specify the response format in your JSON payload.
- Supports up to 4,096 characters per request
- Specify voice, format, and speed in JSON
- Optional language code for non-English scripts
Receive Audio
The API processes your request using the tts-1 or tts-1-hd model. You will receive the audio data directly in the response body, ready for immediate use in your production pipeline. Failed requests incur no charge, ensuring you only pay for successful generations.
- Instant response with audio data
- No charge for failed requests
- Real-time generation for short phrases
Download MP3/WAV
Choose from MP3, WAV, Opus, FLAC, or PCM formats to suit your platform’s requirements. The generated files include an inaudible watermark marking them as synthetic speech, helping maintain transparency with your audience while keeping file sizes manageable.
- Available formats: MP3, WAV, Opus, FLAC, PCM
- Inaudible watermark for synthetic identification
Technical Details
The API endpoint follows the standard OpenAI speech schema, allowing you to use existing SDKs by simply updating the base URL to https://api.playmk77.com/v1. Authentication is handled via a Bearer token in the Authorization header.
OpenAI Compatible
Send a POST request to /v1/audio/speech with your model, input text, and voice selection. The request structure mirrors the OpenAI format, so no complex rewrites are needed for your integration code.
- Base URL: https://api.playmk77.com/v1
Multiple Formats
Choose between mp3, wav, opus, flac, or pcm depending on your production needs. MP3, WAV, Opus, FLAC, and PCM are available formats to suit your platform’s requirements.
- mp3, wav, opus, flac, pcm
Rate Limits
New accounts start with 10 requests per minute. After your first top-up, the limit increases to 60 requests per minute per key. Requests are processed sequentially, so longer texts may queue briefly.
- 10 req/min (initial)
- 60 req/min (after top-up)

Pricing for Creators
MindVoice charges $0.01 per 1,000 characters, making it easy to budget for long meditation scripts or quick fitness cues. Failed requests are free, so you only pay for successful audio generation.
Pay Per Character
Rates are flat: $10 per million characters, regardless of voice or format. This predictable cost helps you scale from a few daily videos to hundreds without surprise invoices.
- $0.01 per 1,000 characters
- Failed requests are free
- Flat rate for all voices
No Monthly Fees
There are no subscriptions, seats, or minimum spend requirements. You top up your balance using USDT on the TRON network, and funds never expire.
Free Trial
Sign in with Google to receive $0.50 in credit, enough for about 50,000 characters over 7 days. Email-based accounts start without trial credit.
- $0.50 credit with Google sign-in
- Valid for 7 days
- Approx. 50,000 characters
Data Privacy
Your creative assets matter. We process your input text solely to generate the audio response and do not use it for model training or improvement. This ensures your unique scripts remain yours, preserving the integrity of your meditation or fitness content without contributing to larger public datasets.
No Training Data
Input text is used exclusively for synthesis. Input text is used only to produce the audio and is not used for training.
No Storage
Generated audio files are returned directly in the response and are not stored on our servers after delivery. We retain only request metadata—such as timestamp, character count, and status—for billing purposes, ensuring transparency without hoarding your creative files.
Secure Keys
Each account is secured with a single active API key. You can issue a new key at any time, immediately invalidating the old one. This simple rotation mechanism ensures that if a key is compromised, your access stops instantly with no lingering risk.
Start Creating
Turn your meditation scripts into professional audio without the learning curve. Our API is designed to fit seamlessly into your existing workflow, letting you focus on content creation rather than infrastructure management.
Whether you are producing daily guided sessions or high-energy fitness tracks, getting started takes just minutes. We provide clear documentation and instant access to the tools you need to scale your audio production.
Get API Key
Sign up on our get-api-key page using Google or your email to receive your unique API key immediately. This key allows you to make requests to the API endpoint and manage your account.
You can issue a new key at any time, which instantly invalidates the old one for security. Your account dashboard displays your balance, character usage, and a ready-to-use curl example to help you begin.
- Sign up with Google or email
- Receive a unique Bearer token
- Instant access to dashboard and balance
Try Demo
New accounts signed in with Google receive $0.50 of free trial credit, valid for seven days. This allows you to generate approximately 50,000 characters of audio to test voice quality and latency before committing to a top-up.
You can experiment with different voices like Aria for calm narration or Felix for energetic coaching to find the perfect tone for your specific content niche.
- $0.50 free trial credit
- Valid for 7 days
- Test all 8 voice presets
Read Docs
Our documentation provides complete details on the request structure, including required fields like model, input, and voice. You can see examples for all supported response formats, from MP3 to WAV, and understand how to handle rate limits effectively.
Explore the endpoint specifications to integrate directly with your preferred programming language using standard HTTP libraries or the OpenAI SDK.
- Request structure examples
- Rate limit guidelines
- Voice and format details

Community & Support
We prioritize clear communication for creators who need reliable answers. Our support team handles inquiries via email, ensuring you get specific guidance without the noise of live chat queues.
Access our curated FAQ for quick solutions to common integration questions, and stay informed about minor service updates through our official channels.
Email Support
We do not offer phone numbers or live chat. All support is conducted via email, allowing for detailed, thoughtful responses to your technical or billing questions.
Our team is dedicated to helping fitness and meditation creators resolve issues efficiently. You can expect clear, written answers without waiting on hold.
FAQ
Browse frequently asked questions covering voice selection, character counting, and API integration tips. This resource helps you get started faster without opening a ticket.
Find answers to common queries about language support, rate limits, and payment methods like USDT top-ups.
Updates
Stay informed about service status and minor improvements through our official channels. We keep updates transparent and relevant to content creators.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Content creators blend calming breathwork with mindful movement to build authentic wellness engagement.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- Creative Commons Attribution 4.0
- LibriTTS-R paper (arXiv 2305.18802)
- Python documentation
- ISO 639 language codes
- Node.js documentation
- openai-node on GitHub
- LibriTTS-R corpus (OpenSLR 141)
- LibriVox public-domain audiobooks
- OpenAI API reference: create speech
- openai-python on GitHub
- W3C WAI: making audio and video accessible
