Frequently asked questions
Are you affiliated with OpenAI?
No. We are an independent storefront for a distinct text-to-speech API. Our endpoint structure mimics OpenAI’s speech endpoint for SDK compatibility, but we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons.
Who owns the voice rights?
Our eight preset voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. We provide consistent, licensable speech for your animation projects without requiring you to hire voice actors for every draft.
Is the editorial team based in the US?
The provided product facts do not specify the geographic location of our editorial or development team. We operate as a cloud API service accessible globally, supporting 23 languages including English, Spanish, and Japanese, without regional office constraints.
Do you offer enterprise contracts?
No. We do not offer enterprise contracts, SLAs, or uptime guarantees. Our model is simple: no monthly plans, no seats, and no minimum spend. You pay only for what you use via USDT top-ups or trial credit.
Is there an SLA guarantee?
No. We do not provide an SLA or uptime guarantee. Requests are processed one after another, so under load a request may wait in a queue. Typical speed is roughly real time, but latency can vary based on server load.
Can I get a refund?
Failed requests are free, and the charge is returned in full if synthesis fails. For successful requests, the facts do not specify a general refund policy. Your balance does not expire, so you can use unused funds whenever needed.
Do you store my text input?
No. Input text is used only to produce the audio and is not used for training. We keep request metadata (time, characters, status) strictly for billing purposes. Your creative content remains yours and is not repurposed for our models.
Is the audio stored after generation?
No. Generated audio is returned in the response and not stored on our servers. Once you receive the audio file via your API call, we do not retain a copy of the generated speech for future use or storage.
Can I contact you by phone?
No. We do not have a phone number or live chat. Support is available by email only. If you have questions about your API key, billing, or technical integration, please reach out via our contact page or support email.
Do you have a physical office?
The product facts do not list a physical office address. We are a cloud-based API service. Our infrastructure is distributed, allowing you to send text and receive audio files globally without needing to visit a specific physical location or data center.
Is the site secure?
We use standard HTTPS for API requests. Authentication is handled via Bearer tokens in the Authorization header. We do not claim specific certifications like SOC 2 or HIPAA. Your API key is the primary security mechanism for accessing your account.
Can I use the voices in a movie?
Yes. Our voices are based on licensed recordings and public-domain readings, providing licensable speech. You can use the generated audio in animations, cartoons, and films. Each file carries an inaudible watermark marking it as synthetic speech, which is standard for TTS.
Are the voices royalty-free?
The voices are based on CC BY 4.0 and public-domain sources, making them highly licensable for commercial use. You pay a flat rate of $10 per million characters. There are no ongoing royalties or per-seat fees for using the generated audio.
Do you sell data to third parties?
No. Input text is used only to produce the audio and is not used for training. Request metadata is kept for billing. We do not sell your data to third parties. Your usage and text inputs remain private to your account.
Who We Are
ToonVoce exists to streamline the animation pipeline by replacing expensive voice actor sessions for draft iterations with a reliable, consistent TTS API. We help agencies turn scripts into character voices without hiring talent for every pass, ensuring your creative direction stays intact from concept to final render.
Our Mission for Animators
We built ToonVoce to remove the bottleneck of scheduling and hiring voice actors for every script revision. By providing eight distinct voice presets across 23 languages, we allow animation teams to rapidly test character dynamics and narrative pacing using consistent, licensable speech that matches your artistic vision without the logistical overhead of traditional recording sessions.
Editorial Team Overview
Our team combines technical expertise in text-to-speech APIs with a deep understanding of animation production pipelines.
Why We Chose Open Source Voices
Every generated file carries an inaudible watermark marking it as synthetic speech. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), sourced from LibriVox public-domain audiobook readings. This foundation allows us to offer transparent, licensable speech directly to animation agencies without the legal ambiguity of proprietary voice cloning.
This approach ensures that your character voices are distinct, clear, and ready for commercial use in your animated projects, from short drafts to final productions.
- LibriTTS-R licensed under CC BY 4.0
- Based on LibriVox public-domain recordings
- Inaudible synthetic speech watermark in every file
Voice Licensing
ToonVoce delivers consistent, licensable speech for animation agencies by leveraging high-quality recordings from the LibriVox public domain project. Our eight voice presets are derived from these source recordings, ensuring that every generated audio file carries an inaudible watermark identifying it as synthetic speech while maintaining the natural cadence of professional narration.
LibriVox Recordings Explained
Our voices are based on licensed recordings from LibriTTS-R, a dataset created from LibriVox public-domain audiobook readings. Each voice preset captures the distinct timbre and pacing of these source recordings, providing animators with reliable character options without the variability of hiring multiple voice actors for every draft.
- Voices derived from LibriTTS-R dataset
- Source material from LibriVox public domain
CC BY 4.0 Usage Rights
The underlying recordings are available under the Creative Commons Attribution 4.0 International License. This framework allows us to integrate these voices into our API while ensuring clear usage rights for our clients. You can generate commercial audio files without worrying about complex royalty structures, provided you adhere to the standard licensing terms.
Public Domain Audiobook Sources
We select audio from public domain audiobooks, which are free from copyright restrictions on the underlying text and performance. This source ensures that the voice models we provide are stable and licensable, allowing animation agencies to produce content across 23 languages with confidence in the audio's legal standing.
Technical Specifications
The API uses a standard POST request to https://api.start11.info/v1/audio/speech. Send your text (up to 4096 characters) as a JSON body with fields like model, input, voice, and response_format. You can use the official OpenAI SDKs by simply changing the base_url to https://api.start11.info/v1 and providing your API key.
API Endpoint Structure
Use POST https://api.start11.info/v1/audio/speech for generation. Include model ("tts-1" or "tts-1-hd"), input text, voice preset, and response_format. Add speed (0.25–4.0) and optional language codes. Other endpoints include GET /v1/voices for details and GET /v1/models.
Supported Audio Formats
Choose from mp3, wav, opus, flac, or pcm. Select the format that best fits your animation pipeline. MP3 is efficient for web delivery, while WAV or FLAC offers lossless quality for post-production. PCM is available for raw audio processing.
Rate Limits and Queuing
Keys are limited to 60 requests per minute (10/min before top-up). Requests process sequentially, so long texts or high load may cause queuing. For texts over 4,096 characters, split them into parts and join the resulting audio files. Typical speed is roughly real time (about 25 characters per second).
Failed requests incur no charge. Ensure your client handles retries efficiently to avoid hitting rate limits unnecessarily.
Data Policy
ToonVoce processes your input text solely to generate the requested audio file. We do not use your scripts, character names, or dialogue to train our speech models or improve the engine, ensuring your creative IP remains distinct from our training data.
Input Text Usage
Your text is transmitted to the API, converted into audio, and the result is returned to you in the response stream. Input text is used only to produce the audio and is not used for training.
Metadata Retention for Billing
We retain minimal metadata—specifically the timestamp, character count, voice used, and request status—to accurately calculate your usage and process charges. This data is stored exclusively for billing transparency and dispute resolution, and is not used for marketing or profiling.
Audio Storage Policy
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. You retain full ownership of the resulting audio files, which carry an inaudible synthetic watermark to identify them as AI-generated content.
Technical Limitations
ToonVoce is a straightforward text-to-speech API designed for animation workflows that prioritize speed and consistency. We focus on delivering clear, licensable audio without the complexity of additional markup or real-time buffering.
Our limitations are intentional, keeping the service simple and cost-effective for studios generating multiple voice drafts.
No SSML Support
We do not support Speech Synthesis Markup Language (SSML). You cannot control pauses, emphasis, or pronunciation rules via XML tags.
Text is processed as plain input. For precise timing, split your script into separate API requests or post-process the audio in your editing software.
- Plain text input only
- No XML tags for pauses or emphasis
- No custom pronunciation dictionaries
No Custom Voice Cloning
We offer eight preset voices derived from licensed recordings, but we do not provide custom voice cloning. You cannot upload a sample to create a unique voice model.
Each voice has a fixed tone: from the warm narrator Aria to the deep documentary style of Orion. This ensures consistency across your projects without the variability of AI cloning.
- Eight fixed presets only
- No upload-based voice training
- No custom voice design
No Streaming or WebSocket
The API returns complete audio files upon request completion. There is no WebSocket connection for real-time partial audio streaming.
For long scripts, you must split the text into chunks of 4,096 characters. Each chunk generates a separate audio file that you join later.
Requests are processed sequentially, so under load, synthesis may wait in a queue before returning the final file.
- Returns full audio files
- No real-time streaming
- Sequential request processing
Support Structure
We keep our support simple and direct. All inquiries go through email, ensuring your question is logged and addressed by a human rather than an automated bot. This approach works well for animation agencies that need clear, written records of technical discussions and billing clarifications.
Email-Only Support
There is no phone number to call and no live chat widget on the screen. You send an email to our support team, and they handle everything from API key issues to voice selection questions in writing.
Response Times
Since we do not have a large call center, each message receives personalized attention. , but email remains the best way to get a detailed answer.
No Live Chat or Phone
We do not offer live chat or voice support. This keeps our overhead low, which helps us keep the per-character pricing affordable for your animation projects. If you need a quick status check, the API documentation covers most common errors.

Contact and Feedback
ToonVoce operates as a lean, independent API provider, which means we prioritize asynchronous communication to keep our engineering team focused on voice synthesis rather than phone tags. We do not offer live chat or phone support, ensuring that every query receives thoughtful attention from someone who understands the technical details of our engine.
Address Details
This address serves as our legal and billing correspondence point, though day-to-day operations are conducted remotely across time zones.
How to Reach Us
Please include your API key and a clear description of your issue in the subject line. Since we handle all support via email, please allow up to 48 hours for a response, depending on the volume of requests.
Feedback Channels
We value direct input from animation agencies on voice quality and language support. While we do not guarantee immediate implementation, all feedback is reviewed by our product team to guide future voice model improvements.
Pricing and Payment
ToonVoce charges $0.01 per 1,000 characters, including spaces and punctuation. Failed requests are free, with charges returned in full. There are no monthly plans, seats, or minimum spend requirements.
Character-Based Pricing
Our API costs $10 per 1 million characters. This flat rate applies to both tts-1 and tts-1-hd models. You only pay for successful synthesis.
USDT TRC-20 Top-Ups
Top-up via USDT on the TRON network (TRC-20) only. Minimum deposit is $5. Credits are automatic within minutes. No cards, PayPal, or VAT invoices.
Free Trial Details
Google sign-ups receive $0.50 credit (approx. 50,000 characters) for 7 days. Email accounts start without trial credit. Balance does not expire.
Languages and Voices
ToonVoce supports 23 languages, allowing animation agencies to localize content globally without hiring new talent for every dialect. Our eight preset voices deliver consistent, licensable speech across these regions, ensuring your characters sound authentic whether they are speaking English, Japanese, or Swahili.
23 Supported Languages
We support 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, giving you flexibility in casting.
8 Distinct Voice Presets
Choose from four female voices (aria, nova, luna, sage) and four male voices (felix, milo, atlas, orion). Each preset offers a distinct tone, from warm narration to energetic promo styles, perfect for diverse character archetypes.
- aria: warm, clear narrator
- nova: bright, upbeat
- luna: soft, storytelling
- sage: calm, instructional
- felix: energetic, promo
- milo: friendly, conversational
- atlas: neutral, news
- orion: deep, documentary
Language Detection Logic
If the language field is omitted, the system guesses the language from the script. Latin text defaults to English, so you must explicitly set the language parameter for non-English Latin-script text to ensure accuracy.
Account Management
ToonVoce accounts are created directly on our /get-api-key/ page using either a Google sign-in or a standard email and password combination. Each account is tied to this specific site, ensuring clear separation of credentials and usage history.
Google and Email Sign-Up
Signing in with Google grants an immediate $0.50 trial credit valid for seven days. Accounts created via email and password start without this trial credit, allowing you to choose the method that best fits your agency’s onboarding workflow.
API Key Management
Each account maintains one active API key for authenticating requests. You can issue a new key at any time; the previous key stops working immediately upon generation, providing simple security control without complex rotation periods.
- Issue a new key instantly via the dashboard.
- Old keys become invalid the moment the new one is created.
Balance and Usage Tracking
The dashboard displays your current balance, remaining trial credit, and total characters processed. You can view a ready-to-use cURL example alongside your real-time usage stats to monitor costs against your animation production volume.
Common Misconceptions
ToonVoce is an independent API provider, not a subsidiary or partner of OpenAI. While our endpoint structure mirrors the OpenAI speech API for easier integration, our engines, voices, and billing are entirely separate. We do not use OpenAI’s infrastructure, nor do we claim to offer their specific model capabilities.
Not Affiliated with OpenAI
We use a compatible JSON request shape and base URL pattern, so you can switch by changing one base_url string in the OpenAI SDK. However, our tts-1 and tts-1-hd models use the same engine and price.
No Enterprise Contracts
We operate as a self-serve API without dedicated enterprise agreements, custom SLAs, or assigned account managers. Every agency, from small studios to large productions, uses the same standard pricing and rate limits (60 requests per minute per key). There are no volume discounts or negotiated terms.
No SLA Guarantees
We do not promise specific uptime percentages or financial credits for downtime. While we aim for reliability, requests are processed in a queue and may wait under load. We do not offer on-premise installations, data-center choices, or certifications like SOC 2 or HIPAA for this API service.
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.
