Frequently asked questions
Is the Hindi text to voice service natural sounding?
Our Hindi TTS uses eight distinct voices based on licensed recordings from LibriVox public-domain audiobook readings. Each voice, such as the warm narrator Aria or the energetic Felix, delivers clear, professional narration suitable for podcast intros, shows, and ads without sounding robotic.
Can one voice speak multiple languages?
Yes, every voice can speak any of our 23 supported languages, including Hindi, English, and Spanish. If you do not set the language parameter, the system guesses it from the script, but for non-English Latin-script text, we recommend explicitly setting the language code.
How much does it cost to generate a 10-minute podcast episode?
Audio generation takes roughly real time, producing about 25 characters of text per second of audio. A 10-minute episode contains approximately 15,000 characters. At our rate of $0.01 per 1,000 characters, generating that episode costs exactly $0.15, with no hidden fees.
Do I need to pay monthly for access?
No, there are no monthly plans, subscriptions, or seats. You simply top up your balance with USDT on the TRON network. Your balance does not expire, and you only pay for the characters you actually use, with no minimum spend required.
Can I use the generated audio in commercial podcasts?
Yes, you can use the generated audio files for commercial podcasts, shows, and ads. Every generated file carries an inaudible watermark marking it as synthetic speech.
What formats are available for download?
You can choose from five response formats: mp3, wav, opus, flac, and pcm. These options allow you to select the best balance of quality and file size for your specific podcast production workflow, whether you need compressed audio or lossless files.
Does the API handle long scripts automatically?
The API does not automatically split long scripts; you must split them into parts of up to 4096 characters and join the resulting audio files. This ensures each request stays within the character limit while allowing you to maintain control over the final audio structure.
Is there a limit on characters per request?
Yes, each request can contain up to 4096 characters of input text. If your script exceeds this limit, you need to split it into multiple requests. Spaces and punctuation count toward this character limit, so plan your text accordingly for optimal results.
How fast is the generation process?
Generation speed is roughly real time, processing about 25 characters of text per second of audio. Short phrases take a few seconds, while longer texts take longer. Requests are processed sequentially, so under heavy load, a request may wait in a queue before starting.
Can I change my API key if it gets compromised?
Yes, you can issue a new API key at any time from your account dashboard. When you generate a new key, the old one stops working immediately, ensuring that any compromised credentials are instantly invalidated without needing to wait for a manual review.
Do you store the audio files I generate?
No, generated audio is returned in the response and is not stored on our servers. We only keep request metadata, such as time, character count, and status, for billing purposes. Your input text is used only to produce the audio and is not used for training.
Is my input text used for training models?
No, your input text is used solely to produce the audio file and is not used for training our models. We respect your content privacy, ensuring that the text you send for synthesis remains isolated from our training datasets and model development processes.
What happens if a request fails?
If synthesis fails, the charge is returned in full to your balance. You can retry the request or split your text differently. This ensures you only pay for successful audio generations, protecting your budget from wasted credits due to temporary errors or issues.
Do you offer refunds for failed requests?
Yes, failed requests are free, and the charge is returned in full automatically. You do not need to contact support for a refund; the system handles it instantly. This applies to any request where the synthesis process did not complete successfully.
First request
curl
curl https://api.playli789.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 Podcasters Choose Our API
Podcast publishers need a reliable voice that matches their brand across every episode. Our API delivers consistent narration from text, ensuring your show’s identity stays uniform.
Consistent Voice Identity
Choose from eight distinct presets like Aria for warm narration or Atlas for neutral news tones. Each voice maintains a stable character profile, so your audience recognizes the tone immediately, regardless of the episode length.
- Eight distinct voice presets
- Consistent character profiles
- Uniform tone across episodes
Cost-Effective Production
Generate audio for just $0.01 per 1,000 characters. This flat rate eliminates the variable costs of hiring voice actors for every script, making it affordable to produce high volumes of content without breaking your budget.
- $0.01 per 1,000 characters
- No per-hour actor fees
- Flat rate pricing
Simple Integration
Our endpoint matches the standard OpenAI request shape. You can use existing OpenAI SDKs by simply changing the base URL, allowing you to integrate speech generation into your workflow without learning a new API structure.
- OpenAI SDK compatible
- Standard JSON requests
- Easy base URL change
Voice Catalog Overview
Our voice catalog offers eight distinct presets designed for consistent audio quality across your podcast episodes. Each voice has a distinct tone, so your audience recognizes the style immediately.
All voices support 23 languages, including Hindi, allowing you to maintain a unified brand identity even when producing content for global audiences.
Female Narrators
Aria provides a warm, clear narration ideal for storytelling. Nova offers a bright, upbeat energy perfect for lively segments.
Luna delivers soft, storytelling tones for intimate monologues, while Sage brings a calm, instructional presence suitable for educational content.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male Narrators
Felix delivers energetic, promo-style reads that capture attention quickly. Milo offers a friendly, conversational tone that feels like a natural host.
Atlas provides a neutral, news-style delivery for clear information delivery. Orion brings a deep, documentary voice for serious or atmospheric content.
All eight voices can speak any of our 23 supported languages, ensuring flexibility for diverse podcast formats.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Style Variations
Each voice maintains a stable character profile, ensuring your audience recognizes the tone immediately. You can adjust the speed between 0.25x and 4.0x to fit your pacing needs.
All voices are based on licensed recordings from LibriTTS-R and LibriVox, providing high-quality, natural-sounding speech without the need for custom voice cloning.

Language Support
Our API supports Hindi text-to-speech alongside 22 other languages, enabling podcast publishers to produce content 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.
You can assign any of the eight distinct voices to any supported language, allowing for flexible narration styles across different episodes or series without needing separate voice talent.
Hindi Text to Voice
We provide high-quality Hindi narration using our standard voices. The engine handles Devanagari script, ensuring accurate pronunciation for your Hindi-language podcasts.
Multi-Language Coverage
Beyond Hindi, we cover major global markets. Whether you are producing content in Spanish, French, or Japanese, the same API endpoint delivers consistent audio quality across all 23 supported languages.
- Latin-script languages default to English unless specified.
- Non-English Latin text requires explicit language code setting.
Auto-Detection
If you do not specify the language field, the system guesses the language based on the text script. For Latin-script text, it defaults to English. For non-English Latin text, we recommend setting the language parameter explicitly to ensure accuracy.
How It Works
The API endpoint accepts your script and converts it into high-quality audio. You simply send a POST request with your text, selected voice, and language preferences to receive a downloadable audio file.
Send Text
Submit up to 4,096 characters per request. If your script exceeds this limit, split it into parts and join the resulting audio files.
Receive Audio
Synthesis typically takes a few seconds for short phrases. For longer texts, processing is roughly real-time (25 characters per second), though requests queue under load.
Format Options
Choose from mp3, wav, opus, flac, or pcm. This flexibility ensures compatibility with your existing podcast publishing workflows and hosting platforms.
Pricing Model
We charge $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. This predictable rate simplifies budgeting for episodic content or ad campaigns without surprise overages.
Per Character Rate
Prices are set at $10 per million characters. Failed requests incur no charge, ensuring you only pay for successfully generated audio files.
No Hidden Fees
There are no monthly plans, seats, or minimum spend requirements. We do not use PayPal or credit cards; top-ups are made via USDT (TRC-20) on the TRON network, with a $5 minimum. Balances never expire, and no VAT invoices are issued.
Trial Credit
New accounts created via Google sign-in receive $0.50 in trial credit, valid for seven days. Email-based accounts start with zero balance. This allows you to test voice quality before committing to a top-up.

Technical Specs
Our API follows a familiar structure, making integration straightforward for podcast production pipelines. You can use standard HTTP methods to send text and receive audio files directly.
The system is designed to integrate with tools you already use. By adjusting the base URL, you can leverage popular SDKs without rewriting your core logic, saving development time for your team.
API Endpoint
Send your narration text to POST https://api.playli789.com/v1/audio/speech. The endpoint accepts a JSON body with fields for model, input text, voice selection, and optional parameters like speed or language code.
It mirrors the standard speech endpoint shape, so you can simply change the base URL in your preferred SDK to point to our API domain.
- POST https://api.playli789.com/v1/audio/speech
- JSON body with model, input, voice, and format options
SDK Compatibility
Since our request structure matches the OpenAI speech endpoint, official OpenAI SDKs work seamlessly. Just update the base_url to https://api.playli789.com/v1 and use your API key for authentication.
You do not need a proprietary library; standard HTTP clients or the widely adopted OpenAI SDKs handle the integration efficiently.
Rate Limits
Each API key allows 60 requests per minute once your account is active. New accounts start with a limit of 10 requests per minute until the first top-up is processed.
This ensures fair usage while allowing you to generate multiple podcast segments or ad reads quickly during production hours.
Audio Quality
Our audio output is generated from licensed recordings and carries an inaudible watermark to clearly mark it as synthetic speech. This ensures transparency while maintaining high production value for your podcast episodes.
The voices are based on the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings, providing a distinct, human-sounding quality without the need for custom voice design.
Synthetic Watermark
Every generated audio file includes an inaudible watermark. This subtle marker identifies the content as synthetic speech, helping maintain clarity for your audience and listeners.
Licensed Source
Our voices are derived from the LibriTTS-R dataset, licensed under CC BY 4.0, and public-domain audiobook readings from LibriVox. This foundation provides narration without the cost of custom voice design.
Clear Output
The API delivers crisp audio files in your chosen format (mp3, wav, opus, flac, or pcm). The output is optimized for podcast standards, ensuring clear narration for intros, ads, and long-form content.
Use Cases
Consistent narration saves time and budget. Podcast Voice Lab generates intros, outros, and ad reads from your script in seconds. Choose from eight distinct voices to match your show’s tone without hiring additional talent.
Long-form content becomes manageable. Split texts into 4096-character chunks and join the audio files. This workflow ensures professional quality for episodic content without the logistical cost of studio bookings.
Intro/Outro Generation
Generate consistent show openers and closings instantly. Select a voice that matches your brand identity, from the warm narration of Aria to the calm instruction of Sage.
Ensure every episode starts and ends with the same professional tone. No scheduling conflicts, no studio downtime.
- Consistent brand voice across episodes
- Instant generation from text
- No voice actor scheduling needed
Ad Reads
Deliver clear, engaging ad reads for sponsors. Use energetic voices like Felix or conversational tones like Milo to drive listener engagement.
Produce multiple variations quickly to test different ad copies. All outputs include an inaudible synthetic watermark for easy identification.
- High-energy promo voices
- Quick variation testing
- Clear, commercial-grade audio
Long-Form Content
Convert full scripts into audio seamlessly. The API handles texts up to 4096 characters per request; you must split and join longer episodes.
Ideal for audiobooks or detailed episode narratives. Processing takes roughly real-time, making production predictable and efficient.
- Handles long scripts via chunking
- Real-time generation speed
- Automated audio joining

Get Started
Start by creating an account on our /get-api-key/ page. You can sign in quickly with Google or set up a standard email and password. This gives you access to your unique dashboard where your API status is tracked.
Sign Up
Accounts are created per site, ensuring your credentials are isolated to this storefront. If you use Google, you receive a $0.50 trial credit valid for seven days, enough for about 50,000 characters. Email-only accounts start without trial credit.
Get Key
Once registered, your dashboard displays your active API key and current balance. You can issue a new key at any time, which immediately invalidates the old one. Use this key in the Authorization header for all requests.
First Request
Send a POST request to https://api.playli789.com/v1/audio/speech with your text and desired voice. The API returns an audio file in your chosen format. For longer scripts, split the text into chunks of 4,096 characters and join the results.
- Endpoint: POST /v1/audio/speech
- Auth: Bearer tts-<your-key>
- Input: JSON body with 'input' and 'voice'
- Format: mp3, wav, opus, flac, or pcm
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Captivating audio storytelling transforms passive listeners into devoted subscribers, driving sustained growth for forward-thinking publishing houses today.
23 languages
Any voice speaks any of these languages.
