Frequently asked questions
Can I use the free trial for TikTok?
Yes. The free trial provides $0.50 of credit, valid for 7 days, allowing approximately 50,000 characters of generation. This is available when signing in with Google. Accounts created with email and password start without trial credit. Failed requests are free, ensuring no charge for errors.
How do I choose the right voice?
Select from eight presets: aria, nova, luna, sage, felix, milo, atlas, or orion. Each voice has a distinct tone, such as warm narration or energetic promo. Voices are based on licensed recordings from LibriTTS-R and LibriVox. All voices support all 23 available languages, allowing flexible casting for diverse content.
What is the best audio format for TikTok?
MP3 is a common format for TikTok uploads. You can also choose WAV, OPUS, FLAC, or PCM via the response_format field. The API returns the audio file directly in the response for immediate use.
How long does it take to generate audio?
Generation takes roughly real time, approximately 25 characters per second. Short phrases may take a few seconds. Requests are processed sequentially, so high load may cause queue delays. The API is optimized for consistent throughput, ensuring predictable timing for automated content pipelines and batch processing workflows.
Can I edit the audio after generation?
Yes. The API returns standard audio files (MP3, WAV, etc.) that you can edit in any audio software. The generated file includes an inaudible watermark identifying it as synthetic speech. You can trim, mix, or add effects to the file before uploading it to your social media platform.
Do I need to credit the voice?
No specific credit is required by the API. The audio contains an inaudible watermark marking it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R and LibriVox public-domain readings. You retain full usage rights for the generated audio files without additional attribution obligations to the voice actors.
How do I handle long scripts?
Split text into parts of up to 4096 characters per request. Generate each part separately and join the resulting audio files. The API does not support SSML or long-form input natively. This method ensures reliable generation and allows you to manage character limits effectively for longer TikTok scripts or Shorts.
Can I use multiple languages in one video?
Yes. The API supports 23 languages, and any voice can speak any supported language. Set the language field to the ISO code for each segment. If not set, the system guesses the language, defaulting to English for Latin script. This allows seamless mixing of languages within a single video project.
What is the character limit per request?
Each request accepts up to 4096 characters in the input field. Spaces and punctuation count toward this limit. For longer content, split the text into multiple requests and concatenate the audio outputs. This ensures consistent quality and prevents timeouts, allowing precise control over audio generation for your content pipeline.
How do I pay with USDT?
Top up using USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are added automatically within minutes after the transfer. There are no monthly plans or subscriptions. Balance does not expire, and you only pay for the characters you actually use at $0.01 per 1,000 characters.
Is the API reliable for production?
The API supports standard rate limits of 60 requests per minute per key. Requests are processed sequentially, which may cause delays under high load. There is no SLA or uptime guarantee. Failed requests are free, ensuring you are not charged for errors in your automated workflows.
Can I automate the process?
Yes. The API uses a standard JSON endpoint compatible with the OpenAI SDK. You can send POST requests from any programming language or automation tool. Use the base_url to integrate seamlessly into your content pipeline. Rate limits allow for batch processing, and failed requests are automatically refunded.
What if the audio is poor quality?
Failed requests are free, so you are not charged for errors. If the audio does not meet your standards, you can regenerate it. The voices are consistent, but you can adjust speed (0.25–4.0) or try different voices. Support is available by email if you encounter specific technical issues with generation.
Do I need technical skills?
Basic technical skills are helpful but not required. The API uses standard HTTP requests and JSON bodies, similar to OpenAI. You can use the provided curl examples or the OpenAI SDK. For non-technical users, the dashboard provides a ready-to-use key and balance tracking, simplifying the integration process for content creation.
Preparation
Begin by creating an account on playa001.com using Google or email. This establishes your identity for the ClipSpeak API, allowing you to manage credits and generate audio files for your TikTok, Reels, or Shorts content.
Account Creation
Sign up via the /get-api-key/ page. Google sign-in provides a $0.50 free trial (valid 7 days), while email accounts start without credit. Accounts are specific to this site.
API Key Generation
Once registered, your dashboard displays your unique API key. Use this key in the Authorization: Bearer header. You may issue a new key at any time; the old one stops immediately.
- Use the key for all API requests.
- One active key per account.
Credit Funding
Top up your balance using USDT on the TRON network (TRC-20). Minimum deposit is $5. Credits appear automatically within minutes. No credit cards or subscriptions are required.
- USDT (TRC-20) only.
- Minimum $5 deposit.
- No monthly plans.
Script Writing
Script preparation defines the quality of the final voiceover. Each API request accepts a maximum of 4096 characters, including spaces and punctuation. For longer TikTok scripts, split the text into multiple segments and join the resulting audio files sequentially to maintain consistency.
Character Limits
Keep individual payloads under 4096 characters. Exceeding this limit causes request failure. Plan your script length accordingly to avoid truncation or additional processing overhead.
- Maximum 4096 characters per request
- Spaces and punctuation count toward the limit
- Split long texts into multiple requests
Language Selection
- Supports 23 languages including English, Spanish, and German
- Default detection assumes English for Latin script
- Explicit language setting recommended for clarity
Text Formatting
Send plain text only. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. Remove complex markdown or special formatting to ensure smooth synthesis. Avoid relying on implicit tone; the voice presets (e.g., Aria, Felix) determine the delivery style.
- No SSML support
- Plain text input only
- Voice preset determines tone

API Request
The API endpoint is POST https://api.playa001.com/v1/audio/speech. Requests use standard JSON bodies compatible with the OpenAI SDK by setting the base_url to https://api.playa001.com/v1. This allows seamless integration into existing automation pipelines without custom client code.
Authentication requires an Authorization header with your Bearer key. The service processes requests sequentially, so high-volume creators should account for queue times during peak usage periods.
Endpoint Usage
Send POST requests to the speech endpoint. The system accepts standard HTTP methods and returns audio files directly in the response body. Ensure your client handles binary audio data correctly.
- Use POST method only
- Set base_url to api.playa001.com/v1
- Include Bearer token in headers
JSON Payload
The request body must include the model (tts-1 or tts-1-hd), input text (max 4096 characters), voice preset, and response_format. Optional fields include speed (0.25–4.0) and language ISO code. Spaces and punctuation count toward the character limit.
Failed synthesis returns a full refund. Ensure text encoding is UTF-8 to avoid processing errors.
- model: tts-1 or tts-1-hd
- input: string, max 4096 chars
- voice: one of 8 presets
- response_format: mp3, wav, opus, flac, pcm
- speed: 0.25–4.0
- language: optional ISO code
Voice Selection
Choose from eight licensed voices: aria, nova, luna, sage, felix, milo, atlas, or orion. Each voice supports all 23 available languages. If the language field is omitted, the system guesses the language from the script, defaulting to English for Latin text.
Set the language parameter explicitly for non-English Latin-script content to ensure accurate pronunciation and tone matching for your TikTok or Reels content.
- aria: warm narrator
- nova: bright upbeat
- luna: soft storytelling
- sage: calm instructional
- felix: energetic promo
- milo: friendly conversational
- atlas: neutral news
- orion: deep documentary
Audio Processing
Upon receiving a successful response, the API returns the audio file directly in the response body. You can save this file immediately to your local storage or pipeline for further processing.
The generated audio is a discrete file, not a stream. Ensure your integration handles the binary data correctly to avoid corruption during storage.
Download Audio
The API returns the audio file directly in the response body upon success. Your application should capture this binary data and write it to your local storage or content pipeline immediately.
Ensure your HTTP client handles binary responses correctly to prevent file corruption. Failed requests return no audio, so verify the status code before saving.
- Capture binary data from the response body
- Verify HTTP 200 status before saving
- Store files with unique identifiers to prevent overwrites
Format Conversion
You may select the output format via the response_format parameter: mp3, wav, opus, flac, or pcm. MP3 is recommended for most social media uploads.
If your editing software requires a different format, use standard conversion tools. For example, convert FLAC or WAV to MP3 before uploading to TikTok or Instagram Reels.
- mp3: Standard for web and social media
- wav/flac: High quality, larger files
- pcm: Uncompressed raw audio
- opus: Efficient compression
Editing
Each API call generates a single audio segment. For longer scripts, you must split the text into parts of up to 4096 characters and join the resulting audio files manually.
Use standard audio editors to remove silence, adjust volume, or add background music. The synthetic watermark is inaudible and does not require removal for commercial use.
- Join multiple segments for long scripts
- Add background music or sound effects
- Trim silence at start/end if needed
Integration
The API integrates directly into your content production pipeline by returning standard audio files that plug into any video editor or automation script. This eliminates manual recording steps and ensures consistent voiceovers for short-form video platforms.
By treating speech synthesis as a simple HTTP call, you can decouple script generation from audio rendering, allowing parallel processing of multiple assets.
Video Editing
Generate audio files via the API, then import them into your editing software as standard media assets. The returned formats (mp3, wav, opus) are compatible with all major non-linear editing systems used for TikTok, Reels, and Shorts production.
This method allows editors to adjust timing, add background music, or sync lip movements without re-recording voice lines.
- Import standard audio formats directly into editing timelines
- Sync generated speech with visual cuts precisely
- Maintain consistent audio levels across multiple clips
Automation
Use the API endpoint in scripts to trigger audio generation when a new video script is finalized. This enables headless production where voiceovers are created automatically before video rendering begins.
Combine with scheduling tools to publish content with pre-generated audio, reducing manual intervention for high-volume creators.
- Trigger TTS generation via webhooks or cron jobs
- Integrate with Zapier or Make.com for workflow automation
- Automate batch processing for multiple video variations
Workflow
Structure your pipeline to handle up to 60 requests per minute, allowing efficient batch processing of voiceovers for daily content schedules.
Ensure your script segmentation aligns with the 4096-character limit to avoid manual splitting during integration.
This approach maintains a steady flow of audio assets ready for video assembly, minimizing bottlenecks in the creation process.
- Batch process up to 60 requests per minute
- Segment scripts to fit within character limits
- Streamline handoff between script and audio teams
Optimization
Optimize audio output by adjusting the speed parameter between 0.25 and 4.0 to fit tight video timelines. Selecting the appropriate voice preset ensures consistent tone across clips, while a final quality check confirms audio integrity before upload.
Speed Adjustment
The speed field accepts values from 0.25 to 4.0. Accelerating speech reduces generation time for short phrases, while slowing it down improves clarity for instructional content. Requests are processed sequentially, so extreme speeds may affect queue latency during high load.
Voice Matching
Choose from eight presets based on content style: nova for upbeat reels, sage for tutorials, or atlas for news-style shorts. Each voice supports all 23 listed languages. Set the language field explicitly for non-English Latin text to prevent incorrect guessing.
- Female voices: aria, nova, luna, sage
- Male voices: felix, milo, atlas, orion
Quality Check
Verify the downloaded audio file before embedding it into your video editor. Check for clear pronunciation and consistent volume levels. Remember that every file contains an inaudible synthetic watermark, which does not affect playback but confirms the audio is API-generated.
Common Issues
Creators often encounter predictable hurdles when generating voiceovers at scale. Understanding these constraints prevents wasted credits and ensures your audio clips remain synchronized with video timelines.
Text Truncation
Each API request accepts a maximum of 4,096 characters. If your script exceeds this limit, you must split the text into smaller segments before sending requests.
- Count characters carefully, including spaces and punctuation.
- Concatenate the resulting audio files after generation.
Language Mismatch
The API guesses the language from the script’s script, defaulting to English for Latin characters. For non-English Latin-script text, explicitly set the language parameter to avoid incorrect pronunciation.
- Supported languages include Spanish, German, and Japanese.
- Unsupported languages like Vietnamese or Thai will default incorrectly.
Rate Limits
Your API key allows 60 requests per minute. New accounts start with a limit of 10 requests per minute until the first top-up is processed. Under load, requests may queue, delaying generation.
- Monitor usage via the dashboard.
- Implement exponential backoff in automation scripts.

Best Practices
Adhering to the 4096-character limit per request ensures reliable synthesis without truncation. For longer scripts, split the text into logical segments and join the resulting audio files to maintain coherence.
Short Segments
Keep individual requests under 4096 characters to avoid truncation. Split longer scripts into logical segments and join the resulting audio files for seamless playback.
- Limit each request to 4096 characters
- Join segments via audio editing software
Clear Script
Use simple punctuation and standard spelling to aid language detection. The API guesses language from the script; explicit language codes improve accuracy for non-English Latin text.
- Use standard punctuation
- Set language codes for non-English text
Consistent Tone
Select a single voice preset for the entire video to maintain auditory continuity. Avoid switching voices between segments to prevent jarring transitions for the viewer.
- Use one voice per video
- Avoid voice switching in segments
Cost Management
Understanding character-based billing is essential for predictable costs in high-volume content creation. Our pricing structure charges $0.01 per 1,000 characters, including spaces and punctuation, ensuring transparent cost calculation before generation begins.
Character Counting
Every character in your input text contributes to the final bill. This includes spaces, punctuation, and special characters. Ensure your script is precisely counted to avoid unexpected charges, as each request is evaluated individually.
- Space counts as one character
- Punctuation marks are included
- Special characters are billed normally
Budget Tracking
Monitor your usage directly from the dashboard. The interface displays your current balance, remaining trial credit, and total characters processed. This real-time visibility helps you stay within budget without manual calculations.
- Real-time balance updates
- Trial credit visibility
- Character usage history
Top-Up Strategy
Funds are added via USDT (TRC-20) on the TRON network. The minimum top-up is $5, and credits are available within minutes. There is no expiration on your balance, allowing you to fund your account as needed for sustained content production.
- Minimum $5 top-up
- USDT TRC-20 only
- Credits do not expire
Tools and SDKs
We leverage the OpenAI SDK for seamless integration, requiring only a base_url change to our API endpoint. This allows you to use familiar libraries without learning a new client. The request structure mirrors standard TTS endpoints, ensuring compatibility with existing automation scripts.
For lightweight needs or quick testing, cURL provides a direct HTTP interface. Python scripts can automate bulk generation by iterating through text arrays and handling responses programmatically. These tools support the high-volume workflows typical for TikTok and Reels content pipelines.
OpenAI SDK
Use the official OpenAI SDK by setting base_url to https://api.playa001.com/v1. Authenticate with your tts-... key in the Authorization header. This method ensures type safety and easy error handling within your preferred programming environment.
- Compatible with existing OpenAI client implementations
- Supports standard JSON request bodies
cURL
Ideal for direct API testing or simple shell scripts. Send a POST request to /v1/audio/speech with your JSON payload. This approach requires no external libraries, making it suitable for CI/CD pipelines or quick manual checks.
- Direct HTTP communication
- No dependency installation required
- Easy to debug network issues
Python Scripts
Python scripts can loop through text arrays, split long scripts, and join audio files automatically. Use the requests library for raw HTTP calls or the OpenAI SDK for structured responses. This is optimal for automating daily content production.
- Automate bulk audio generation
- Integrate with video editing libraries
- Handle character splitting logic
Licensing
All generated audio files are granted for commercial use in TikTok, Reels, and Shorts content. You may monetize videos without additional licensing fees or recurring royalties. The API key holder retains full rights to the generated audio assets for their specific use cases.
Attribution is not required for the synthetic voice itself. However, you must adhere to platform-specific guidelines regarding AI-generated content. Ensure your video metadata accurately reflects synthetic voice usage if required by social media platforms.
Commercial Use
All generated audio files are granted for commercial use in TikTok, Reels, and Shorts content. You may monetize videos without additional licensing fees or recurring royalties. The API key holder retains full rights to the generated audio assets for their specific use cases.
Attribution
Attribution is not required for the synthetic voice itself. However, you must adhere to platform-specific guidelines regarding AI-generated content. Ensure your video metadata accurately reflects synthetic voice usage if required by social media platforms.
Watermark
Every generated file carries an inaudible watermark that marks it as synthetic speech. This watermark is embedded in the audio data and cannot be removed without degrading the file integrity. It serves as proof of origin for copyright disputes.
The watermark is transparent to the listener and does not affect playback quality on any device or platform. It remains intact across standard format conversions such as MP3, WAV, or OGG.
- Inaudible to human listeners
- Embedded in audio data

Support
Support is provided exclusively via email. There are no live chat widgets, phone numbers, or SLA guarantees for response times. For immediate technical issues, refer to the documentation or check your error logs before contacting us.
Email Support
Send all inquiries to [email protected]. Include your API key, request ID, and relevant logs for faster resolution. We do not offer priority tiers.
Documentation
The /docs/ page contains complete endpoint specifications, example payloads, and error code definitions. It is the primary resource for integration troubleshooting.
Error Logs
Review your account dashboard for usage metadata and status codes. Logs include request time, character count, and failure reasons to help diagnose synthesis issues without email support.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Selecting the correct voice ensures consistent audio branding across TikTok, Reels, and Shorts videos.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- W3C WAI: making audio and video accessible
- curl documentation
- LibriTTS-R paper (arXiv 2305.18802)
- openai-node on GitHub
- LibriTTS-R corpus (OpenSLR 141)
- Node.js documentation
- FFmpeg documentation
- OpenAI API reference: create speech
- openai-python on GitHub
- Creative Commons Attribution 4.0
- LibriVox public-domain audiobooks
