Frequently asked questions
What is voice cloning?
We offer eight preset voices based on licensed LibriTTS-R and LibriVox recordings, not custom voice cloning. Each preset delivers a distinct style—from warm narrators to deep documentary tones—without requiring you to hire actors. Every generated audio file includes an inaudible watermark to clearly mark it as synthetic speech, ensuring transparency for your YouTube content while maintaining high-quality consistency.
How does voice cloning work?
We don’t offer custom voice cloning. Our system uses eight preset voices based on licensed recordings. You send text via a POST request to our API endpoint, and we return an audio file. The engine processes requests sequentially, so under load, a request may wait in a queue. Longer texts are split into 4096-character parts and joined automatically.
Is voice cloning expensive?
Pricing is simple: $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 only pay for the characters you actually generate successfully.
Can I clone my own voice?
No, we do not offer custom voice cloning. You cannot upload your own voice or design a new one. Instead, choose from eight presets like Aria, Nova, or Atlas. These voices are based on licensed recordings and are ready to use immediately via the API.
What is the difference between TTS and voice cloning?
TTS converts text into audio. Our API uses eight preset voices derived from licensed recordings. While we call this ‘voice cloning’ because the voices mimic specific character types, they do not replicate a single real person like a celebrity. Unlike custom cloning, you cannot train a new voice model; you simply select from our existing eight options.
Do I need to pay for each video?
You pay based on character count, not per video. The rate is $10 per 1 million characters. If you have multiple videos, you simply sum the characters across all requests. There are no per-video fees or subscription costs. Your balance deducts automatically as you generate audio for your content.
Can I use cloned voices commercially?
Yes, you can use the generated audio commercially. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings. Every generated file includes an inaudible watermark identifying it as synthetic speech.
How many languages are supported?
We support 23 languages, including English, Spanish, German, French, Japanese, and Chinese. Any voice can speak any of these languages. If you do not set the language parameter, the system guesses from the script, defaulting to English for Latin text. Vietnamese, Thai, and Ukrainian are not supported.
Do I need technical skills to use the API?
Basic technical skills are helpful but not required. The API uses standard JSON bodies and works with the official OpenAI SDKs by changing the base URL. You can also use ready-made curl examples provided on the dashboard. No-code users can integrate the API into their workflows using simple HTTP requests or tools.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. The system processes requests sequentially, so under heavy load, a request might wait in a queue before timing out. Check your dashboard for usage logs to see status and character counts for billing.
Is there a free trial available?
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 with USDT on the TRON network (TRC-20) for a minimum of $5 to continue generating audio.
How long does voice generation take?
Typical speed is roughly real-time, generating about 25 characters of text per second. Short phrases may take a few seconds. Requests are processed one after another, so under load, a request may wait in a queue. Longer texts are split and joined, which may add slight processing time.
Can I change my voice mid-sentence?
No, you cannot change voices mid-sentence within a single request. Each request specifies one voice from the eight presets. To change voices, you must send separate requests for different text segments and join the resulting audio files. The API does not support SSML or complex markup for voice switching.
Are there any hidden fees?
No hidden fees. Pricing is strictly $10 per 1 million characters. Failed requests are free. Top-ups via USDT on TRON (TRC-20) are credited automatically within minutes. There are no monthly plans, seats, or VAT invoices. Your balance does not expire. You only pay for the characters you successfully generate.
First request
curl
curl https://api.playuk9.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.mp3What is Voice Cloning?
Voice cloning for YouTube isn’t magic; it’s synthetic speech built from licensed sources. Our engine uses recordings from LibriTTS-R (CC BY 4.0) and public-domain LibriVox readings, creating distinct presets rather than mimicking specific celebrities. This approach ensures clear usage rights without complex actor negotiations.
Synthetic vs. Cloned Voices
Unlike deepfake audio that mimics a specific person’s unique timbre, our voices are presets derived from licensed datasets. They sound natural but remain distinct synthetic characters. This clarity helps viewers understand they are listening to generated content, not a real person’s unrecorded performance.
How TTS Engines Work
You send text to our API, and we return an audio file. The system processes your input up to 4,096 characters per request, generating audio that matches the selected voice preset. It’s a straightforward request-response workflow, perfect for automating video narration without manual recording.
Why Consent Matters
Ethical cloning relies on the source material’s license. Since our voices come from CC BY 4.0 and public-domain audiobooks, you avoid the headache of clearing rights for individual actors. However, always disclose synthetic audio in your videos to maintain trust with your audience.
Why You Should Clone Voices
Voice cloning creates a consistent audio identity across your channel, ensuring your audience recognizes your content instantly. This consistency strengthens brand loyalty and keeps viewers engaged, even as you scale your output.
Efficiency in content creation is crucial for YouTube creators. With our API, you can generate high-quality narration in seconds, eliminating the need for expensive voice actors or recording studios. This allows you to produce more videos without compromising on quality.
Creative freedom without casting means you can experiment with different voices and tones without the logistical hassle of hiring. Our preset voices, like Aria for warm narration or Nova for upbeat content, offer flexibility that helps you find the perfect tone for your videos.
Consistency Across Videos
Maintaining a consistent voice across all your videos helps build a strong brand identity. Viewers can instantly recognize your content, which enhances engagement and retention.
This consistency is achieved through our reliable TTS API, which ensures uniform quality and tone across all generated audio files.
- Uniform audio quality
- Brand recognition
- Viewer engagement
Efficiency in Content Creation
Generate narration in seconds, allowing you to produce more content without the need for expensive voice actors or recording studios.
Our API integrates seamlessly into your workflow, enabling you to create videos faster and more efficiently.
- Fast generation
- Cost-effective
- Scalable
Creative Freedom Without Casting
Experiment with different voices and tones without the logistical hassle of hiring. Our preset voices offer flexibility to find the perfect tone for your videos.
No need to coordinate schedules or negotiate rates with voice actors. Our API provides instant access to a variety of voices.
- Flexible options
- No hiring needed
- Instant access

How Our API Works
Our API turns text into audio files via a simple POST request to https://api.playuk9.com/v1/audio/speech. Send your script in JSON, specify a model like tts-1, and receive the generated audio instantly.
Text-to-Speech Basics
Send text (up to 4096 characters) via JSON. The engine processes it and returns the audio file directly. We support mp3, wav, opus, flac, and pcm formats, giving you flexibility for YouTube uploads or editing workflows.
Simple Integration
Use the official OpenAI SDKs by changing the base_url to https://api.playuk9.com/v1. Authenticate with your tts-... API key in the header. It works exactly like the standard speech endpoint, so your existing code adapts easily.
No Coding Required
No-code creators can use simple HTTP requests or our cURL examples. Just input your script, select a voice like Aria or Nova, and get your audio file. No complex pipelines or engineering teams needed to start creating.
Preset Voices You Can Use
Aria: Warm Narrator
Aria delivers a warm, clear narration style ideal for educational content or structured updates. Her voice cuts through background noise effectively, ensuring your message is understood without requiring complex audio engineering.
Nova: Bright Upbeat
Nova brings a bright, upbeat energy to your videos. This preset is perfect for fast-paced vlogs, product showcases, or energetic introductions where you need to capture attention immediately.
Luna: Soft Storyteller
Luna offers a soft, storytelling tone that works beautifully for narrative-driven content. Use her voice for calm explanations, personal stories, or segments that benefit from a gentle, engaging delivery.
Ethical Voice Cloning
We source our voice presets from licensed recordings in the LibriTTS-R dataset and LibriVox public-domain audiobook readings. This means your generated audio rests on a clear legal foundation, using established material rather than relying on unverified or unknown sources for your YouTube content.
Licensed Recordings
Our eight preset voices are based on the LibriTTS-R dataset and public-domain readings from LibriVox. This provides a transparent origin for the synthetic voices you use in your videos, ensuring the underlying data has a known provenance.
- Based on LibriTTS-R (CC BY 4.0)
Inaudible Watermarks
Every audio file generated through our API carries an inaudible watermark that clearly marks the content as synthetic speech. This allows you to maintain transparency with your audience and platforms regarding the use of AI-generated voiceovers in your productions.
Clear Usage Rights
Because we utilize licensed and public-domain sources, you can integrate these voices into your YouTube videos with confidence. The synthetic nature is marked, but the source material is established, simplifying your content rights management without needing to track down individual voice actors.

Supported Languages
VoiceBloom supports 23 languages, allowing you to produce content for a global audience without hiring multiple voice actors. Our engine handles diverse scripts, ensuring clear and natural-sounding audio for creators reaching viewers worldwide.
We do not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, or Bengali. If your content targets these markets, you may need a different solution. However, for the 23 supported languages, you have full freedom to mix and match.
23 Languages Available
You can generate audio in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, or Turkish. Any of our 8 preset voices can speak any of these languages.
For Latin-script text that isn’t English, you should explicitly set the language parameter. Otherwise, the system defaults to English. This ensures accurate pronunciation and intonation for non-English content.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi
- Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Multi-Language Support
Mix languages within your workflow. Use English for your primary narration and switch to Spanish or French for specific segments. The API handles each request independently, so you control exactly which language is generated for each part of your script.
Global Reach
Expand your YouTube channel’s reach by dubbing existing content. With support for major global languages, you can localize your videos efficiently. Simply adjust the text and select the appropriate voice to match your target region’s linguistic needs.
Pricing That Scales
VoiceBloom charges a flat rate of $0.01 per 1,000 characters, making budgeting predictable for your YouTube channel. Spaces and punctuation count toward the total, so you can estimate costs directly from your script. Failed requests are free, so you only pay for successful audio generation. This pay-per-character model ensures you never overpay for unused capacity or unexpected usage spikes during high-volume publishing days.
Pay Per Character
Our pricing is straightforward: $10 per 1 million characters. There are no hidden fees for format changes or speed adjustments. You can monitor your exact usage and remaining balance directly in your account dashboard, ensuring complete transparency as your channel grows.
- Flat rate: $0.01 per 1,000 characters
- Failed requests are refunded in full
- Real-time usage tracking in dashboard
No Monthly Fees
Unlike many competitors, we do not require monthly subscriptions or minimum spend commitments. You only pay for what you use, making it ideal for creators with irregular upload schedules. Whether you publish daily or once a month, your costs align directly with your content output.
There are no seats to manage or team limits to worry about. Your API key scales with your needs, allowing you to generate as many videos as your budget allows without administrative overhead.
- No monthly subscriptions or seats
- No minimum spend requirements
- Perfect for irregular upload schedules
Free Trial Credit
Sign up with Google to receive $0.50 in free trial credit, valid for 7 days. This gives you approximately 50,000 characters to test voice quality and integration without any financial commitment. It is the perfect way to experience the clarity of our preset voices before investing in your channel.
Top-ups are processed instantly via USDT on the TRON network (TRC-20) with a $5 minimum. Your balance never expires, so you can pay for your videos exactly when you need them.
- $0.50 free trial credit for 7 days
- Approx. 50,000 characters to test
- Instant top-ups via USDT (TRC-20)
FAQs for Creators
Voice cloning costs just $10 per million characters, or $0.01 per 1,000 characters. Failed requests are free, and you can start with a $0.50 free trial valid for 7 days. Payments are made via USTRC-20 with no monthly fees or subscriptions.
This predictable pricing lets you budget accurately for long-form content without worrying about hidden costs or variable actor rates.
Is Voice Cloning Expensive?
At $0.01 per 1,000 characters, the API is cost-effective for high-volume creators. You pay only for successful generation, and unused trial credit expires after 7 days.
- $0.01 per 1,000 characters
- Failed requests are free
- $0.50 free trial for 7 days
Can I Clone My Own Voice?
Our API uses eight preset voices based on licensed LibriTTS-R recordings from LibriVox. It does not offer custom voice cloning where you upload your own voice. The audio files include an inaudible watermark to mark them as synthetic speech.
- Eight preset voices available
- Licensed recordings from LibriVox
- Inaudible watermark included
How Fast Is Generation?
Generation speed is roughly real-time for long texts, processing about 25 characters of text per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so high traffic might cause slight queue delays.
- ~25 characters per second
- Sequential processing
- Queues during high load

Get Started Today
Start by signing up via Google on the /get-api-key/ page. You instantly receive $0.50 in free trial credit, valid for 7 days, letting you test the API without a credit card or payment details.
Once registered, your unique API key appears on your dashboard. This key authenticates your requests to https://api.playuk9.com/v1. You can also check your balance, usage stats, and a ready-to-use cURL example right there.
Sign Up with Google
Click the Google sign-in button on the registration page. This creates an account linked to your email, granting immediate access to the $0.50 trial credit. No payment method is required to start.
Get Your API Key
After signing in, your dashboard displays your active API key. Use this key in the Authorization: Bearer header for all requests. You can generate a new key at any time, which instantly invalidates the old one.
- Key format:
tts-... - One active key per account
- Instant invalidation on regeneration
Start Cloning Voices
With your key, send a POST request to /v1/audio/speech. Paste your script, select a preset voice like Aria or Nova, and receive an audio file. Split long texts into 4096-character chunks for best results.
- Endpoint:
POST /v1/audio/speech - Supports JSON body
- Works with OpenAI SDKs
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Create stunning videos with ease using our intuitive platform designed for creators.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- IETF RFC 7845: Ogg Opus
- MDN: Web Speech API
- Node.js documentation
- Creative Commons Attribution 4.0
- W3C WAI: making audio and video accessible
- TRON developer hub: TRC-20
- LibriTTS-R corpus (OpenSLR 141)
- openai-python on GitHub
- ISO 639 language codes
- LibriTTS-R paper (arXiv 2305.18802)
- FFmpeg documentation
