Frequently asked questions
Is the free voice over generator truly free?
Yes. Signing in with Google provides $0.50 of credit, valid for 7 days, allowing approximately 50,000 characters. Accounts created with email and password start without trial credit. After the trial expires or balance is depleted, you must top up via USDT (TRC-20) to continue generating audio.
Which voices are best for YouTube narration?
We offer eight presets. For narration, aria provides a warm, clear narrator style, while luna offers soft storytelling. For instructional content, sage is calm, and milo is friendly and conversational. Felix suits energetic promos, atlas covers neutral news, orion handles deep documentaries, and nova is bright and upbeat.
How many languages does the API support?
The API supports 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. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.
Can I use the API for commercial YouTube videos?
Yes. The API generates audio files that you can use in your YouTube videos. The generated audio carries an inaudible watermark marking it as synthetic speech. Input text is used only for production and not for training. There are no restrictions on commercial usage for generated files.
What happens if the synthesis fails?
Failed requests are free. If synthesis fails, the charge is returned in full. You are only billed for successful audio generations. This ensures you do not pay for audio files that were not delivered successfully to your application.
How do I handle long scripts for YouTube?
Split your text into parts of up to 4096 characters. Send each part as a separate request and join the resulting audio files. This allows you to generate longer content while staying within the per-request character limit. The API processes requests sequentially, so queueing may occur under load.
Is there a limit on characters per request?
Yes, each request accepts up to 4096 characters in the input field. Spaces and punctuation count toward this limit. For longer scripts, you must split the text into multiple requests, generate the audio for each part, and then concatenate the resulting audio files.
Do I need to pay for USDT to use the API?
You must top up with USDT on the TRON network (TRC-20) to continue after your trial or balance is exhausted. The minimum top-up is $5. Credits are credited automatically within minutes after the transfer. No cards, PayPal, or subscriptions are supported. Balance does not expire.
How fast is the audio generation?
Typical speed is roughly real time for long texts, about 25 characters per second of generation. Short phrases may take a few seconds. Requests are processed one after another, so under load, a request may wait in a queue before synthesis begins.
Can I change the voice speed?
Yes. You can adjust the speed parameter between 0.25 and 4.0. This allows you to make the narration faster or slower to fit your video pacing. The speed adjustment applies to all voices and languages supported by the API.
What audio formats are available?
You can request audio in mp3, wav, opus, flac, or pcm formats. Specify the desired format in the response_format field of your request. The API returns the generated audio file in the specified format directly in the response.
Is the voice synthetic or human-recorded?
The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. However, every generated file carries an inaudible watermark that marks it as synthetic speech. The output is generated by the TTS engine, not a direct playback of the source recording.
Do I get an invoice for payments?
No. There are no invoices with VAT. Payments are made via USDT on the TRON network. Request metadata (time, characters, status) is kept for billing purposes, but no formal invoice document is provided. Accounts are per site, and billing is transparent based on character usage.
How do I contact support?
Support is by email only. There is no phone number or live chat available. You can reach the support team via the contact page or email address provided on the site. Response times are not guaranteed as there is no SLA or uptime guarantee.
First request
curl
curl https://api.playbd11.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.mp3API-First Workflow
VocalSync is built as a pure REST API. You send a JSON payload to the speech endpoint and receive an audio file. This structure allows agencies to integrate voice synthesis directly into their existing production pipelines without custom middleware.
The endpoint accepts standard parameters like model, input text, voice, and speed. Because the request shape matches the OpenAI Speech API, you can reuse existing codebases by simply updating the base URL.
JSON Request Format
Every request is a standard POST to /v1/audio/speech with a JSON body. The input text is capped at 4,096 characters. For longer scripts, split the text into chunks and join the resulting audio files.
You define the voice, speed (0.25–4.0), and output format. The API returns the audio file in the response body.
- POST /v1/audio/speech
- JSON body with text, voice, and format
- Max 4,096 characters per request
OpenAI SDK Compatible
Use the OpenAI SDKs (or plain HTTP). Change the base_url to https://api.playbd11.com/v1 and inject your API key. The request structure is identical, so no code refactoring is needed for standard calls (provided the base_url is updated).
This compatibility ensures that existing automation scripts written for other providers can be redirected to VocalSync with minimal configuration changes.
- OpenAI SDK compatible
- Change base_url only
- No code refactoring needed
Simple Integration
Authentication is handled via a Bearer token in the Authorization header. One key per account simplifies management. Generate your key on the /get-api-key/ page and start sending requests immediately.
No complex setup or proprietary libraries are required. Standard HTTP clients work perfectly, making it easy to add TTS to any server-side application or CI/CD pipeline.
- Bearer token auth
- One active key per account
- Standard HTTP clients work
Voice Selection
VocalSync provides eight distinct voice presets engineered for clarity and consistency, ensuring your YouTube narration maintains a professional tone across all episodes. Each voice is derived from licensed recordings, offering reliable synthetic speech without the variability of random generation.
Female Presets
Four female voices cover distinct tonal needs. Aria offers a warm, clear narration style ideal for documentaries. Nova provides a bright, upbeat tone for energetic content. Luna delivers a soft, storytelling voice suitable for narrative videos. Sage ensures calm, instructional clarity for educational material.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
Male Presets
Four male voices provide versatile options for different content types. Felix brings an energetic, promo-ready tone. Milo offers a friendly, conversational style. Atlas delivers a neutral, news-like delivery. Orion provides a deep, documentary-style voice for serious topics.
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Clear Narration
All voices are built on licensed recordings from LibriTTS-R, ensuring high-fidelity output. Every generated file includes an inaudible watermark to identify synthetic speech, maintaining transparency for your audience. The consistent voice profiles allow agencies to standardize audio branding across multiple channels without re-recording.
Language Support
VocalSync supports 23 languages, including English, Spanish, Hindi, Japanese, and German. Any voice can speak any of these languages, allowing agencies to produce consistent narration across global markets without managing multiple voice actors.
Input text is processed using standard ISO codes. If the language is not specified, the system guesses the language based on the script, defaulting to English for Latin-script text.
23 Supported Languages
The API supports Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Languages like Vietnamese, Thai, and Ukrainian are not supported.
- Arabic, Chinese, Danish, Dutch, English, Finnish
- French, German, Greek, Hebrew, Hindi, Italian
- Japanese, Korean, Malay, Norwegian, Polish, Portuguese
- Russian, Spanish, Swahili, Swedish, Turkish
Automatic Detection
When the language field is omitted, the model infers the language from the input script. Latin-script text defaults to English, so non-English Latin text should explicitly set the language parameter to ensure correct pronunciation.
Manual Language Tagging
Pass an ISO code in the language field to force specific language output. This ensures accuracy when mixing scripts or when automatic detection might misidentify the target language.
Audio Formats
Choose the optimal audio format for your YouTube workflow based on file size and quality needs. VocalSync supports standard compression and lossless options to fit your delivery pipeline.
MP3 Compression
MP3 is the default choice for web playback, offering small file sizes that load quickly on YouTube and social platforms. It reduces bandwidth costs while maintaining clear speech intelligibility for narration.
- Ideal for standard YouTube video uploads
- Smallest file size for efficient storage
- Broad compatibility with all video editors
Lossless WAV
WAV provides uncompressed PCM audio, preserving the full fidelity of the generated voice. Use this format when editing audio in professional software to avoid generation artifacts from repeated compression cycles.
- Raw audio data without compression loss
- Best for post-production editing workflows
- Larger file sizes suitable for local storage
FLAC and Opus
FLAC offers lossless compression, reducing file size by ~50% compared to WAV without sacrificing quality. Opus provides efficient lossy compression.
- FLAC: Lossless with smaller footprint than WAV
- Opus: High efficiency for streaming or archiving
- Both maintain high audio integrity
Pricing Model
VocalSync charges $0.01 per 1,000 characters, with a flat rate of $10 per million characters. Spaces and punctuation count toward the total. Failed requests incur no charge, ensuring you only pay for successful synthesis.
Pay Per Character
Pricing is transparent and based solely on input length. At $10 per million characters, costs scale linearly with volume, making it predictable for high-frequency agency workflows.
No Monthly Fees
There are no subscriptions, seats, or minimum spends. You top up via USDT (TRC-20) and use your balance until it is exhausted. The minimum top-up is $5.
- No monthly plans or recurring billing
- No per-seat licensing fees
- No minimum spend requirements
Free Trial Credit
Sign in with Google to receive $0.50 in credit (approx. 50,000 characters), valid for 7 days. Email-based accounts start with zero balance.

Performance
Text-to-speech generation typically runs at roughly real-time speed, processing approximately 25 characters of text per second of audio. Short phrases may take a few seconds to synthesize, while longer scripts scale linearly with duration.
Real-Time Generation
Long-form content is split into 4096-character segments and joined seamlessly. This ensures consistent output without exceeding API limits, maintaining natural pacing for YouTube narration.
Queue Handling
Requests are processed sequentially. Under heavy load, synthesis may wait in a queue before execution begins. This serial processing guarantees accurate character counting and billing without concurrent resource contention.
Speed Control
Adjust playback speed between 0.25x and 4.0x via the speed parameter. This allows precise alignment with video timelines, enabling faster narration for quick summaries or slower pacing for detailed explanations.
Use Cases
VocalSync enables agencies to automate end-to-end YouTube narration pipelines. By integrating the TTS API into production workflows, teams can generate voiceovers from scripts in JSON format, ensuring consistent audio quality across high-volume channels without manual recording overhead.
YouTube Narration
Generate long-form videos efficiently by splitting texts into 4096-character segments. The API returns concatenated audio files, maintaining narrative continuity for documentaries, explainers, and commentary channels without manual stitching.
- Supports 23 languages including English, Spanish, Hindi, and Japanese
- Adjustable speed from 0.25x to 4.0x for pacing control
Agency Workflows
Integrate directly into existing CMS or project management tools using standard HTTP requests. The OpenAI SDK compatibility allows seamless adoption into current engineering stacks, reducing integration time for development teams.
- Single API key manages all voices and languages
- Transparent character-based billing eliminates unexpected costs
Content Scaling
Scale content output without hiring additional voice talent. With a free trial of $0.50 credit and pay-per-character pricing, agencies can test volume capabilities before committing to top-ups via USDT.
- No monthly fees or minimum spend requirements
- Key rotation is available (old key stops immediately).
Technical Specs
VocalSync enforces a rate limit of 60 requests per minute per API key, scaling from 10 requests per minute for new accounts before their first top-up. This ensures stable throughput for agency workflows without overloading the synthesis engine.
Rate Limits
Requests are processed sequentially, so high-volume batches may experience queuing delays during peak load. Each request supports up to 4096 characters; longer texts must be split and concatenated by the client.
Authentication
Secure access is managed via a single active Bearer token passed in the Authorization header. You can issue a new key at any time from the dashboard; the previous key becomes invalid immediately.
Error Handling
Standard HTTP status codes indicate request outcomes. Failed synthesis requests incur no charge, with the credit returned to your balance automatically. Input validation ensures text length and format constraints are met before processing.
Getting Started
Start by creating an account on the /get-api-key/ page using Google or an email and password combination. This grants you access to your dashboard, where you can view your balance, trial status, and usage metrics.
Create Account
Sign up via Google for an immediate $0.50 trial credit (valid for 7 days). Email-based accounts begin without trial credit. Accounts are specific to this site.
Generate Key
Your dashboard displays a single active API key starting with tts-. You can issue a new key at any time; the previous one stops immediately. Use this key for authentication.
- Key format:
tts-... - Auth header:
Authorization: Bearer <key> - One active key per account
First Request
Send a POST request to https://api.playbd11.com/v1/audio/speech with a JSON body. Use the OpenAI SDK by setting base_url to https://api.playbd11.com/v1. Include model, input, and voice fields to receive an audio file.
- Endpoint:
POST /v1/audio/speech - Supported formats: mp3, wav, opus, flac, pcm
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. We empower creators by delivering precise audience insights that drive meaningful engagement for agencies.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- openai-node on GitHub
- W3C WAI: making audio and video accessible
- OpenAI API reference: create speech
- LibriVox public-domain audiobooks
- Creative Commons Attribution 4.0
- LibriTTS-R corpus (OpenSLR 141)
- Python documentation
- curl documentation
- FFmpeg documentation
- LibriTTS-R paper (arXiv 2305.18802)
- ISO 639 language codes
