Frequently asked questions
Is the free tier truly unlimited?
No. The free trial provides $0.50 of credit, valid for 7 days after signing in with Google. This covers approximately 50,000 characters. Accounts created with email and password start without trial credit. There is no permanent free tier; you must top up with USDT (TRC-20) to continue generating audio after the trial expires or the balance is depleted.
Can I use these voices commercially?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. You can use the generated audio files for your YouTube videos and other commercial projects without additional licensing fees beyond the API usage cost. The audio files are returned directly in the response and are not stored by the service.
How do I handle long scripts?
Split your text into parts of up to 4096 characters per request. Generate the audio for each part separately, then join the resulting audio files together. This ensures each request stays within the character limit while allowing you to produce narration for longer videos or podcasts without losing quality or hitting endpoint constraints.
What happens if a request fails?
Failed requests are free. If the synthesis fails for any reason, the charge is returned in full to your account balance. You are only billed for successful audio generations. This ensures you do not pay for audio files that were not delivered, protecting your budget during high-load periods or network issues.
Which formats are best for YouTube?
MP3 is the standard format for YouTube uploads and is fully supported. You can also choose WAV, OPUS, FLAC, or PCM depending on your editing workflow. MP3 offers a good balance of quality and file size for most video platforms. Select your preferred format via the response_format parameter in your API request.
Do I need to credit the voices?
Attribution is not strictly required for commercial use under the CC BY 4.0 license for the source recordings, but it is good practice. The generated audio contains an inaudible watermark marking it as synthetic speech. You are not required to credit specific voices like Aria or Nova.
How fast is the generation?
Generation takes roughly real time, 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. For long texts, splitting into smaller chunks can help manage queue times and ensure consistent delivery speeds.
Can I change my API key?
Yes. You can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This allows you to rotate keys securely without downtime. Each account has one active key at a time, ensuring clear tracking of usage and billing per key.
What languages are supported?
We support 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. If the language is not set, it is guessed from the script, defaulting to English for Latin text.
Is there a speed control?
Yes. You can adjust the speech speed using the speed parameter, which accepts values between 0.25 and 4.0. This allows you to slow down narration for clarity or speed up content for faster-paced videos. Adjusting speed does not affect the character count or pricing of your requests.
Does it support SSML?
No. The API does not support SSML (Speech Synthesis Markup Language). You cannot use SSML tags for pauses, emphasis, or pronunciation within the input text. If you need precise control, you must split your text into separate requests and adjust parameters like speed or voice for each segment manually.
Can I clone my own voice?
No. We do not offer custom voice cloning or the ability to upload your own voice. You must choose from the 8 preset voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, or Orion. These voices are based on licensed recordings and are available for immediate use in your API requests without additional setup.
How is billing calculated?
Billing is based on characters processed at $10 per 1 million characters ($0.01 per 1,000 characters). Spaces and punctuation count as characters. Failed requests are free. You top up using USDT on the TRON network (TRC-20), with a minimum of $5. Balances do not expire, and there are no monthly plans or subscriptions.
What is the character limit per request?
Each request can contain up to 4096 characters of input text. If your script exceeds this limit, you must split it into multiple requests. Each request generates a separate audio file, which you can then join together. This limit applies to the input field in the JSON body of your API call.
First request
curl
curl https://api.playtqtq.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 YouTube Creators Choose This API
Why YouTube creators choose this API centers on predictability and clarity. You get reliable narration without complex pipelines or monthly usage caps. The system is designed for consistent output, allowing you to focus on content creation rather than monitoring tier limits or overage fees.
No Monthly Limits on Usage
Unlike subscription-based platforms that throttle usage or charge overage fees, this API charges strictly per character. You pay $10 per million characters, with no minimum spend or monthly plans. This structure ensures your costs scale directly with your video output, preventing budget surprises during high-volume production weeks.
Copyright-Safe Licensed Voices
All voice models are built from licensed recordings from LibriTTS-R and LibriVox public-domain audiobooks. You can use the generated audio in your YouTube videos. The voices are distinct and synthetic.
Simple OpenAI-Compatible Endpoint
The API uses a familiar POST request structure compatible with OpenAI SDKs. You only need to change the base URL and provide your Bearer token. This simplicity means you can integrate TTS into your existing automation workflows or custom scripts without learning a new proprietary system.
Supported Voices and Languages
PlayTQTQ provides eight distinct voice presets designed for clarity and consistency in long-form narration. Each voice is derived from licensed recordings, ensuring a reliable, copyright-safe audio track for your YouTube videos without complex pipeline management.
8 Distinct Voice Presets
Choose from four female voices: Aria (warm narrator), Nova (upbeat), Luna (soft storytelling), and Sage (calm instruction). Or select male options: Felix (energetic promo), Milo (conversational), Atlas (neutral news), and Orion (deep documentary).
Every generated file carries an inaudible watermark marking it as synthetic speech, distinguishing your content while maintaining professional quality.
23 Languages Including English and Spanish
The API supports 23 languages, including English, Spanish, German, French, Japanese, and Hindi. Any voice can speak any supported language, allowing you to localize content efficiently.
If the language is not explicitly set, the system guesses from the script (defaulting to English for Latin text). For non-English Latin scripts, explicitly set the language parameter for accuracy.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish.
Voice Clarity for Long-Form Content
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain LibriVox audiobook readings. This foundation ensures consistent tone and clarity, even for extended video narrations.
Text is split into 4096-character segments and joined to produce the final audio.
How It Works
To generate speech, send a JSON payload via POST to the API endpoint. Include your text in the input field (max 4096 characters), select a voice from the eight presets, and specify your desired output format. Authentication is handled via a Bearer token in the header.
Send Text via API Request
Structure your request body with the model ('tts-1' or 'tts-1-hd'), the text content, and the voice identifier. You can also adjust the speed between 0.25 and 4.0, or set a specific language ISO code to ensure correct pronunciation, though the system will auto-detect Latin script as English by default.
- Endpoint: POST /v1/audio/speech
- Body: JSON with
input,voice,model - Header:
Authorization: Bearer tts-...
Receive Audio Files Instantly
The API processes your text and returns the audio file directly in the response. For standard texts, generation is near real-time, though queue times may occur under high load. If the synthesis fails, no charge is applied to your balance.
Download MP3 or WAV Formats
Choose mp3 for efficient file sizes suitable for YouTube uploads, or wav for lossless quality. Other supported formats include opus, flac, and pcm. The generated audio includes an inaudible watermark identifying it as synthetic speech, ensuring clarity for your content pipeline.
Pricing for Creators
Pricing for Creators
Our API charges based on actual usage, so you only pay for the text you convert. There are no monthly plans, seats, or minimum spend requirements. This model is designed for YouTube creators who produce content irregularly, ensuring you never pay for idle capacity.
Pay Per Character Used
We count every character in your input, including spaces and punctuation. You receive a detailed breakdown of characters used and remaining balance in your dashboard. Failed requests are free, so you are not charged for errors.
$10 Per Million Characters
The rate is $10 per 1 million characters, which equals $0.01 per 1,000 characters. This consistent pricing applies to all voice presets and languages. You can top up your balance using USDT (TRC-20) on the TRON network, with a minimum deposit of $5.
Free Trial Credit Available
When you sign in with Google, you receive $0.50 of free trial credit. This allows you to generate approximately 50,000 characters over 7 days to test the API. Accounts created with email and password do not include this trial credit.
Technical Requirements
Send a simple HTTP POST request to the API endpoint. The system accepts standard JSON payloads, making it easy to integrate with existing scripts or tools without complex setup.
HTTP POST Requests
Direct your requests to https://api.playtqtq.com/v1/audio/speech. This follows the standard OpenAI-compatible format, allowing you to use familiar SDKs or simple curl commands.
JSON Body Format
Structure your input as a JSON object. Include the model, input text, voice, and response_format. The API processes the text up to 4096 characters per request.
Bearer Token Authentication
Include your unique API key in the request header. Use the format Authorization: Bearer tts-.... This key identifies your account and tracks your character usage against your balance.

Audio Formats and Quality
Select from five standard audio formats to match your editing workflow. Choose MP3 for small file sizes, WAV for lossless quality, Opus for efficient compression, FLAC for archival, or PCM for raw data. Each request returns a single audio file ready for download.
Generation speed is roughly real-time, producing about 25 characters of text per second. Short phrases take a few seconds, while longer texts process sequentially, potentially queuing under load. The output is a complete audio file, not a streaming partial stream.
MP3, WAV, Opus, FLAC, PCM
The API accepts four common formats and one raw option. MP3 offers compressed efficiency, while WAV provides uncompressed lossless audio. Opus is ideal for low-bandwidth needs, FLAC preserves quality without compression artifacts, and PCM delivers raw data for custom processing pipelines.
- MP3: Compressed, widely compatible.
- WAV: Lossless, high fidelity.
- Opus: Efficient, low bandwidth.
- FLAC: Lossless compression.
- PCM: Raw uncompressed data.
Real-Time Generation Speed
Audio generation typically matches real-time speed, averaging 25 characters per second. Short phrases may take a few seconds to process. For longer scripts, requests are handled sequentially, so high load times may introduce queuing delays before synthesis begins.
Unlike streaming solutions, you receive the complete audio file only after processing finishes. This ensures consistent quality but requires waiting for the full duration of the speech before the file is available for download.
Inaudible Synthetic Watermark
Every generated audio file includes an inaudible watermark indicating it is synthetic speech. This mark is embedded in the audio data and is not audible to human ears. It serves as a metadata tag to identify the content as AI-generated without affecting playback quality.
Getting Started
To begin using PlayTQTQ, create an account on our /get-api-key/ page. You can sign in quickly using your Google account or register with a standard email and password. This account is specific to playtqtq.com and holds your API credentials and usage history.
Sign Up with Google or Email
Registration is straightforward and takes only a few seconds. If you use Google sign-in, you automatically receive a $0.50 free trial credit valid for 7 days, giving you about 50,000 characters to test the service. Email-based accounts start with zero balance.
Get Your API Key
Once registered, your dashboard displays your unique API key immediately. This key authenticates all your requests. You can generate a new key at any time, which instantly invalidates the previous one, ensuring your credentials remain secure.
Run Your First Request
Use the official OpenAI SDK or any HTTP client to send a POST request to https://api.playtqtq.com/v1/audio/speech. Provide your API key in the Authorization header, select a voice from the 8 presets, and include your text. The API returns the audio file directly in the response, ready for download.
- Endpoint: POST https://api.playtqtq.com/v1/audio/speech
- Auth: Bearer <your-api-key>
- Body: JSON with model, input, and voice
Use Cases for Content
PlayTQTQ delivers reliable, copyright-safe narration tailored for content creators. Generate synthetic voiceovers in 23 languages with a simple API endpoint, ensuring consistent audio quality for your videos without complex pipelines.
YouTube Video Narration
Generate long-form narration efficiently by splitting scripts into 4096-character chunks. The API joins the audio files seamlessly, maintaining natural flow for documentaries, tutorials, or commentary videos.
Podcast Voiceovers
Create intro/outro segments or fill gaps in your podcast episodes with synthetic voiceovers. Use distinct voices for different characters or segments to add variety without hiring multiple voice actors.
Social Media Shorts
Produce quick, engaging voiceovers for short-form content. With fast generation speeds, you can iterate on scripts rapidly and download MP3s ready for immediate editing and posting.
Frequently Asked Questions
Find clear answers to common questions about our TTS API, from pricing and languages to technical limitations and commercial usage rights for your YouTube content.
Is the free tier truly unlimited?
The free trial provides $0.50 of credit (about 50,000 characters) valid for 7 days when signing in with Google. After that, you top up via USTRC-20 with no monthly limits.
Can I use these voices commercially?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobooks. You can use the generated audio in your videos without additional licensing fees.
How do I handle long scripts?
Split your text into parts of up to 4,096 characters per request. Generate each part separately and join the resulting audio files in your editor.
What happens if a request fails?
Failed requests are free. If synthesis fails, the charge is returned in full to your balance.
Which formats are best for YouTube?
MP3 is the standard for compatibility. You can also choose WAV, Opus, FLAC, or PCM depending on your editing workflow.
Do I need to credit the voices?
Attribution is not strictly required for commercial use under the CC BY 4.0 license of the source recordings, but it is good practice to mention the voice name in your video description.
How fast is the generation?
Generation is roughly real-time (25 characters per second). Short phrases take a few seconds; longer texts may queue under load.
Can I change my API key?
Yes. You can issue a new key at any time from your dashboard. The old key stops working immediately.
What languages are supported?
We support 23 languages including English, Spanish, German, French, Japanese, and Chinese. Any voice can speak any supported language.
Is there a speed control?
Yes. You can adjust the speed between 0.25 and 4.0 using the speed parameter in your API request.
Does it support SSML?
No. This API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control pacing by splitting text.
Can I clone my own voice?
No. We do not offer custom voice cloning. You choose from the 8 available presets.
How is billing calculated?
Pricing is $10 per 1 million characters. Spaces and punctuation count as characters. Balance does not expire.
What is the character limit per request?
Each request accepts up to 4,096 characters of input text. For longer scripts, send multiple requests.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This style helps retain viewer attention by reducing the 'read-aloud' fatigue often associated with standard TTS.
23 languages
Any voice speaks any of these languages.
