Frequently asked questions
Is this custom voice cloning?
No. We do not offer custom voice cloning or uploading your own voice. You choose from eight preset voices like Aria or Felix. These are based on licensed recordings from LibriTTS-R and LibriVox. If you need a unique voice, you must select one of the available presets rather than creating a new one from scratch.
Can I use the audio for commercial cartoons?
Yes. The audio files are generated from licensed recordings under CC BY 4.0 and public-domain sources. You receive the audio directly in the response for your production needs. You receive the audio directly in the response for your production needs. The voices are based on licensed recordings (CC BY 4.0) and public-domain sources.
What is the character limit per request?
Each API request supports up to 4096 characters of input text. For longer scripts, you should split the text into parts of this size and join the resulting audio files. This ensures consistent generation quality and allows you to manage processing time effectively during your animation workflow.
Do voices sound robotic or synthetic?
The audio carries an inaudible watermark marking it as synthetic speech. The voices are based on licensed recordings from LibriTTS-R and LibriVox, providing natural-sounding narration. While they are AI-generated, they offer clear, distinct character tones suitable for animation dialogue without sounding overly robotic or artificial.
How many languages are supported?
We support 23 languages, including English, Spanish, Japanese, and German. Any voice can speak any of these languages. If you do not set the language parameter, it guesses from the script, defaulting to English for Latin text. You must explicitly set the language for non-English Latin-script text.
Can I change the speed of the speech?
Yes. You can adjust the speech speed between 0.25 and 4.0 using the speed parameter in your API request. This allows you to fine-tune the pacing of dialogue for your animation scenes. The default speed provides a natural rhythm, but you can speed up or slow down the output as needed.
Is there a free trial available?
Yes. Signing in with Google gives you a $0.50 credit, valid for 7 days, which covers about 50,000 characters. Accounts created with email and password start without this trial credit. You can test the API quality and integration before committing to a top-up via USDT on the TRON network.
Do I need to pay for failed requests?
No. If a synthesis request fails, the charge is returned in full. You only pay for successful audio generations. This ensures you are not charged for errors or processing issues, allowing you to retry requests without worrying about unnecessary costs for your animation project budget.
Can I clone my own voice for a character?
No. We do not offer custom voice cloning where you upload your own voice. You must use one of the eight preset voices like Nova or Atlas. These voices are based on licensed recordings and provide consistent, licensable speech for your characters without the need for custom cloning technology.
What audio formats can I download?
You can choose from mp3, wav, opus, flac, and pcm formats. Specify the desired response_format in your API request to receive the audio in your preferred codec. This flexibility allows you to integrate the audio directly into your animation pipeline or editing software without additional conversion steps.
How do I integrate with my pipeline?
Send a POST request to our endpoint with your text and parameters. The API returns an audio file directly. You can use the official OpenAI SDKs by changing the base_url to our API address. This standard integration makes it easy to incorporate TTS into your existing animation or development workflows.
Are the voices licensed for public use?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This allows you to use the generated audio in public projects. The voices are based on licensed recordings (CC BY 4.0) and public-domain sources.
Can I use multiple voices in one audio file?
No. Each API request generates audio for a single voice preset. To create a dialogue with multiple characters, you must send separate requests for each voice and then join the audio files in your editing software. This allows precise control over each character's tone and timing.
Is there a minimum spend required?
No. There is no minimum spend or monthly plan. You pay only for what you use, with a rate of $10 per million characters. Top-ups start at $5 via USDT. Your balance does not expire, and you can manage your budget flexibly based on your animation production needs.
First request
curl
curl https://api.start11.info/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 Animation Agencies Choose TTS
Animation agencies often face endless cycles of script revisions, requiring fresh voice actor sessions for every minor dialogue tweak. Our TTS API eliminates this bottleneck by allowing you to generate new audio files instantly via a simple API call. This means you can iterate through multiple script variations rapidly without scheduling studio time or managing talent availability for every draft.
Rapid Script Iteration
With a 60 requests-per-minute limit, you can process a full scene’s dialogue in seconds, though requests are processed sequentially and may wait in a queue under load. If a line needs adjustment, just send the updated text and receive the new audio file immediately, keeping your pre-production workflow moving smoothly without waiting for human availability.
Consistent Character Voices
Maintaining character continuity across different script drafts is critical. Our eight preset voices ensure that Aria or Felix sound identical whether they are speaking in draft one or draft ten. This consistency helps you evaluate pacing before committing to final production.
Cost-Effective Prototyping
Hiring voice actors for rough cuts can be expensive and time-consuming. At $0.01 per 1,000 characters, prototyping dialogue is significantly cheaper. You can test dozens of variations for the price of a single session, ensuring you select the preferred performance before final recording.
Our 8 Preset Voices for Characters
To give your animated characters distinct personalities without hiring multiple voice actors, we offer eight consistent presets. These voices work across 23 languages, ensuring your dialogue remains uniform from draft to final cut.
Female Narrators: Aria, Nova
Aria provides a warm, clear narration ideal for gentle storytelling or instructional segments. Nova brings a bright, upbeat energy perfect for high-energy scenes or commercial-style promos.
Male Leads: Felix, Milo
Felix delivers an energetic, promo-ready tone suitable for action sequences or dynamic advertisements. Milo offers a friendly, conversational style that feels natural for character dialogue and everyday interactions.
Neutral & Deep: Atlas, Orion
Atlas provides a neutral, news-like delivery for clear exposition or documentary-style segments. Orion offers a deep, documentary tone that adds gravity and seriousness to dramatic narratives.
Voice Cloning Explained for Creators
Voice cloning mimics a specific person’s unique vocal characteristics, often used to recreate a specific voice or restore archived narration. While powerful, it requires significant data and processing to capture subtle nuances like breath and emotion accurately.
What is Voice Cloning?
It involves training a model on hours of reference audio to replicate a voice’s timbre and cadence. This allows for generating new speech that sounds like a specific individual, even if they never recorded the script.
Consent and Licensing
Cloning typically requires explicit consent from the voice owner, especially for commercial use. Licensing fees can vary widely depending on the fame of the voice and the scope of distribution.
Why We Use Presets
We focus on eight licensed preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) derived from LibriTTS-R and LibriVox. This ensures consistent, licensable speech without the complexity and legal overhead of custom cloning for every character.
- No custom voice cloning offered
- Licensed recordings from public domain sources
- Consistent quality across 23 languages
Languages for Global Cartoons
For animation agencies producing global cartoons, reaching diverse audiences requires robust multilingual support. Our API enables you to generate consistent dialogue across 23 distinct languages, ensuring your characters sound authentic whether they are speaking English, Japanese, or Swahili.
23 Supported Languages
We support 23 languages, including 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 preset can speak any of these languages, allowing you to maintain character consistency across international markets.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German
- Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian
- Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Latin Script Defaults
If you do not specify a language, the system guesses the language from the script. Text in Latin script defaults to English. For non-English Latin-script text, such as Spanish or German, you should explicitly set the language parameter to ensure accurate pronunciation and tone.
Non-Supported Languages
Our engine does not support Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, or other languages outside the listed 23. When localizing your cartoons, ensure your target language is in the supported list to avoid mispronunciations that could break the immersion for your viewers.
Audio Formats for Editing
Animation editors need precise control over audio assets, which is why our API lets you choose the exact format that fits your pipeline. You can generate files that are immediately ready for web playback or high-quality masters for final compositing.
MP3 for Web
MP3 is the standard for web delivery and quick reviews. It offers small file sizes while maintaining clear dialogue, making it ideal for storyboards and client presentations where bandwidth matters.
WAV for Master Files
WAV provides uncompressed, lossless audio for your final masters. This ensures no quality loss during editing or mixing, preserving the full dynamic range of the generated speech for professional post-production.
Opus and FLAC Options
Opus offers efficient compression, while FLAC provides lossless compression for archivists who want smaller files without sacrificing audio integrity. Both formats integrate seamlessly into modern animation workflows.

How the API Works
Send your script text to our endpoint and receive a synthesized audio file instantly. Each request handles up to 4096 characters; for longer scenes, split the text and join the resulting audio files. Typical generation speed is roughly real-time on long texts; short phrases take a few seconds.
Use the official OpenAI SDKs by pointing base_url to https://api.start11.info/v1. Authenticate with your tts-... key and use standard models like tts-1. This familiar structure lets you integrate directly into your existing animation pipelines using standard HTTP or the OpenAI SDK.
Send Text, Get Audio
Post JSON to POST https://api.start11.info/v1/audio/speech. Include your input text, choose a voice from our eight presets, and specify a response_format like mp3 or wav. The API returns the audio file directly in the response.
- Max 4096 characters per request
- Supports mp3, wav, opus, flac, pcm
- Adjustable speed from 0.25x to 4.0x
OpenAI SDK Compatible
Our endpoint mirrors the OpenAI speech structure. Simply update your SDK configuration to use https://api.start11.info/v1 as the base URL. You can use the same code patterns you already know, ensuring a smooth transition for development teams.
Rate Limits Explained
Each API key is limited to 60 requests per minute. If your queue fills up, requests may wait briefly in line. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed.
Pricing for Animation Volumes
Animation agencies pay only for what they generate: $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed requests are free, so you never pay for errors during your drafting phase.
Pay Per Character
There are no monthly plans, seats, or minimum spends. You can process short phrases or split long scripts into 4,096-character parts, joining the audio files yourself. This model fits the iterative nature of animation production, where dialogue changes frequently.
- $0.01 per 1,000 characters
- No monthly subscriptions
- Failed requests are free
Free Trial Credit
Sign in with Google to receive $0.50 in trial credit, valid for 7 days. This covers about 50,000 characters, enough to test voice consistency across your first few scenes. Accounts created with email and password start without this trial credit.
- $0.50 credit for Google sign-ins
- Valid for 7 days
- Covers ~50,000 characters
USDT Top-Up
Top up your balance using USDT on the TRON network (TRC-20). The minimum deposit is $5, and funds are credited automatically within minutes after the transfer. There are no cards, PayPal, invoices, or VAT charges. Your balance never expires.
- USDT on TRON (TRC-20)
- Minimum $5 deposit
- Automatic credit within minutes
Data Privacy for Studios
We use your input text solely to generate the audio file for that specific request. Your scripts are not ingested into our training datasets, ensuring your original dialogue remains unique to your production.
No Training Data Use
Unlike some consumer-grade services, we do not retain your text for model improvement. The characters you type are processed only to create the voice output and are then discarded from our active processing memory.
Audio Not Stored
Once the audio file is delivered in your API response, we do not store the generated speech. This ensures that your character voices are not cached or reused without your explicit request, keeping your creative assets private.
Metadata for Billing
We retain minimal request metadata—specifically the timestamp, character count, and status—to accurately calculate your usage and apply charges. This data is used exclusively for billing purposes and is not linked to the content of your scripts.
Support and Contact
We handle all inquiries via email at [email protected]. Our team reviews messages and responds within one business day. There are no phone numbers, no live chat widgets, and no instant support queues to fill with generic greetings.
Email Support Only
All communication goes through our dedicated support email. This ensures your technical questions about the API, billing issues, or voice selection queries are logged and addressed by engineers who understand the TTS engine.
- Email: [email protected]
- Response time: within 1 business day
- No phone support available
No Live Chat
We do not offer real-time chat support or live agents. This keeps our operational costs low, allowing us to maintain our simple pay-per-character pricing model without hidden support fees or subscription tiers.
Documentation Access
For most technical questions, our comprehensive documentation is the fastest resource. It includes ready-to-use code examples for the OpenAI SDK, endpoint details for /v1/audio/speech, and a complete list of the 8 preset voices and 23 supported languages.
- API Reference: /docs/
- Code examples included
- Voice and language lists
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Each voice has a distinct tone suitable for standard adult roles in animation.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- W3C WAI: making audio and video accessible
- Python documentation
- TRON developer hub: TRC-20
- openai-node on GitHub
- MDN: Web Speech API
- Tether (USDT)
- LibriTTS-R corpus (OpenSLR 141)
- LibriTTS-R paper (arXiv 2305.18802)
- ISO 639 language codes
- LibriVox public-domain audiobooks
- OpenAI API reference: create speech
