Frequently asked questions
How do I get my API key?
Sign up on the /get-api-key/ page using Google or email plus password. The dashboard displays your active API key, balance, and usage statistics. You can issue a new key at any time, which instantly invalidates the previous one. Each account is tied to this specific site.
What is the base URL for the API?
The API base URL is https://api.288t.info/v1. Use this endpoint for all requests, including POST /v1/audio/speech, GET /v1/voices, and GET /v1/models. This base URL allows you to use standard HTTP clients or SDKs by configuring them to point to this specific domain.
Can I use the OpenAI SDK?
Yes, the official OpenAI SDKs work perfectly. You simply change the base_url to https://api.288t.info/v1 and use your VoxCare API key. The request shape matches the OpenAI speech endpoint, making integration straightforward for developers already familiar with the OpenAI client library structure.
How do I specify the Hindi language?
Include the optional language field set to the ISO code for Hindi in your JSON request body. Although the API guesses language from the script, explicitly setting Hindi ensures accurate synthesis. Hindi is one of our 23 supported languages, and any voice can speak it.
What is the maximum text length?
Each request supports up to 4096 characters of input text. For longer texts, split the content into parts of this size and join the resulting audio files. This limit applies to the input field in your JSON payload sent to the speech endpoint.
How do I handle rate limits?
You are limited to 60 requests per minute per key, or 10 per minute before your first top-up. Requests are processed sequentially, so under load, you may experience queueing delays. Monitor your usage via the dashboard to stay within these limits effectively.
What happens if the request fails?
If synthesis fails, the charge is returned in full, so you are not billed for errors. Failed requests incur no cost. You can retry your request or check the dashboard for status details. This ensures you only pay for successfully generated audio files.
Are there extra costs for HD models?
No, there are no extra costs. Both tts-1 and tts-1-hd use the same engine and price of $10 per 1 million characters. You can choose the model based on quality preference without worrying about different pricing tiers for high-definition audio.
How do I change the voice?
Specify the desired voice name in the voice field of your request body. You can choose from eight presets like aria, nova, luna, sage, felix, milo, atlas, or orion. Each voice can speak any of the 23 supported languages, including Hindi.
Is SSL required for requests?
Yes, use HTTPS for all requests to https://api.288t.info/v1. This ensures secure transmission of your API key and text data. The standard HTTPS protocol is required for the authentication header and payload security when sending text for synthesis.
Can I use the API from a browser?
Yes, you can use the API directly from a browser using standard HTTP requests. Since it is a REST API, you can send POST requests from client-side code. Just ensure you handle your API key securely, as it is visible in browser traffic.
How do I rotate my API key?
Issue a new key from your dashboard at any time. The new key becomes active immediately, and the old one stops working at once. This allows you to rotate keys without downtime. You can generate a new key as often as needed for security.
What is the response format?
You can request audio in mp3, wav, opus, flac, or pcm formats using the response_format field. The API returns the audio file directly in the response. This flexibility allows you to choose the format that best fits your application’s playback requirements.
Do I need to install a library?
No, you do not need to install a specific library. You can use any HTTP client to send requests to the API. Alternatively, you can use the official OpenAI SDK by adjusting the base URL. Plain HTTP requests work just as well for integration.
First request
curl
curl https://api.288t.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.mp3Python (openai)
from openai import OpenAI
client = OpenAI(base_url="https://api.288t.info/v1", api_key="tts-...")
with client.audio.speech.with_streaming_response.create(
model="tts-1", voice="nova", input="Hello from Python.", response_format="mp3"
) as response:
response.stream_to_file("hello.mp3")Node.js (openai)
import OpenAI from "openai";
import fs from "node:fs";
const client = new OpenAI({ baseURL: "https://api.288t.info/v1", apiKey: process.env.TTS_API_KEY });
const res = await client.audio.speech.create({ model: "tts-1", voice: "milo", input: "Hello from Node.js." });
fs.writeFileSync("hello.mp3", Buffer.from(await res.arrayBuffer()));| voice | |
|---|---|
aria | female |
nova | female |
luna | female |
sage | female |
felix | male |
milo | male |
atlas | male |
orion | male |
| language | |
|---|---|
ar | العربية |
zh | 中文 |
da | Dansk |
nl | Nederlands |
en | English |
fi | Suomi |
fr | Français |
de | Deutsch |
el | Ελληνικά |
he | עברית |
hi | हिन्दी |
it | Italiano |
ja | 日本語 |
ko | 한국어 |
ms | Bahasa Melayu |
no | Norsk |
pl | Polski |
pt | Português |
ru | Русский |
es | Español |
sw | Kiswahili |
sv | Svenska |
tr | Türkçe |
Get Your API Key
Start by visiting the /get-api-key/ page on 288t.info to create your account. You can sign up using Google for instant access or provide an email and password for a standard account.
Once registered with Google, you receive a unique API key and $0.50 of free trial credit, valid for 7 days. Accounts created with email and password start without trial credit. This allows you to test Hindi medical text generation immediately without entering payment details.
Sign Up Process
Navigate to the sign-up page and choose your preferred authentication method. The process is designed for indie developers to get started quickly, ensuring you can begin integrating the TTS API into your healthcare applications within minutes.
Google vs Email Auth
Google authentication provides immediate access to your API key and trial balance. Email and password accounts are created without initial trial credit, requiring you to top up before generating your first audio file.
Both methods secure your account and link your usage to a single active key, simplifying billing and rate limit tracking for your projects.
Key Management
Each account holds one active API key. You can issue a new key at any time from your dashboard; the old key stops working immediately, ensuring tight security for your medical data integrations.
Monitor your key's usage, character count, and balance directly on the dashboard to stay within the 60 requests per minute limit.
- One active key per account
- Instant revocation upon rotation
- Dashboard shows balance and usage
First Request with Curl
Sending a POST request to the speech endpoint generates audio from your medical text. The API accepts standard JSON, supporting both standard and high-definition models at the same price. You only pay for characters processed, making it easy to budget for patient guide generation.
Use the cURL command below to send Hindi medical text. Requests are processed sequentially, so under load a request may wait in a queue. Failed requests are free: if synthesis fails, the charge is returned in full.
Basic JSON Body
The request body must include the model, input text, voice, and response format. You can optionally specify a speed between 0.25 and 4.0. The API returns the audio file directly in the response body.
Ensure your input text does not exceed 4096 characters. For longer patient instructions, split the text into chunks and join the resulting audio files manually.
model: "tts-1" or "tts-1-hd"input: Your medical text stringvoice: e.g., "aria" or "mil"
Hindi Text Example
Use the language field to specify Hindi ("hi") to ensure accurate pronunciation. Without it, the system guesses the language, which may default to English for Latin-script text.
Here is a cURL example sending a simple Hindi medical instruction. Replace YOUR_API_KEY with your actual key from the dashboard.
language: "hi"input: "कृपया इस दवा को खाली पेट लें।"voice: "nova"
Response Format
A successful response contains the audio file in the requested format (mp3, wav, opus, flac, or pcm). The status code is 200 OK.
If an error occurs, such as invalid input, the API returns a JSON error object with a descriptive message. No charge is applied for failed requests.
- Status 200: Audio file returned
- Status 400: Invalid input or parameters
- Status 429: Rate limit exceeded
OpenAI SDK Integration
Integrate VoxCare’s Hindi TTS API seamlessly using the official OpenAI SDK. By simply updating the base_url parameter, you can route requests to our endpoint while keeping your existing code structure intact. This compatibility allows indie developers to use our API by changing the base_url, keeping their existing code structure intact.
The API accepts the same request shape as the OpenAI speech endpoint, ensuring smooth migration for teams already familiar with standard TTS workflows. You can leverage existing SDK methods for handling JSON bodies and response parsing, making it easy to add clear audio guides to healthcare apps.
Base URL Change
Update the base_url in your OpenAI SDK client configuration to https://api.288t.info/v1. This directs all API calls to our infrastructure while maintaining the standard request format. No changes are needed to the endpoint path or method, as we mirror the OpenAI speech endpoint structure exactly.
SDK Compatibility
The official OpenAI SDKs work directly with our API. You can use the same library versions you are currently using for OpenAI services. This ensures consistency in your development environment and reduces dependency management overhead for your healthcare application.
Code Snippets
- Set
base_urltohttps://api.288t.info/v1 - Use standard
POSTrequests to/v1/audio/speech - Pass
model,input,voice, andlanguagein JSON body - Handle responses as standard audio bytes or file streams
Voice Selection
VoxCare provides eight distinct voice presets, all capable of speaking any of the 23 supported languages. Each voice is engineered to sound natural and professional, ensuring your patient guides and medical instructions are easy to follow.
List Available Voices
Our library includes four female and four male voices, ranging from warm narrators to neutral newsreaders. You can choose based on the tone that best fits your specific medical context, from instructional to conversational.
- Female: aria, nova, luna, sage
- Male: felix, milo, atlas, orion
Select by Tone
Use aria for clear narration, nova for upbeat updates, luna for storytelling, or sage for calm instructions. Male options include felix for energetic promos, milo for friendly conversations, atlas for neutral news, and orion for deep documentaries.
Hindi Voice Options
Any of our eight voices can speak Hindi fluently. We recommend using the explicit language parameter set to hi to ensure optimal pronunciation for medical terminology, rather than relying on auto-detection which may default to English for Latin-script inputs.
Audio Formats
The API supports MP3, WAV, Opus, FLAC, and PCM formats for flexible integration into healthcare apps. MP3 provides efficient compression for web delivery, while WAV and FLAC offer lossless quality for archival or clinical analysis.
MP3 Support
MP3 is one of the supported formats, balancing file size and compatibility. It is ideal for mobile apps and web players where bandwidth efficiency matters for patient guides.
WAV and FLAC
WAV and FLAC provide uncompressed, lossless audio. Use these formats when precise audio quality is required for clinical recordings or when downstream processing needs raw fidelity without compression artifacts.
PCM Raw Audio
PCM returns raw audio samples. This format is suitable for low-level audio processing pipelines or custom audio engines that handle their own encoding.
Rate Limits
VoxCare enforces a clear rate limit of 60 requests per minute per API key. This cap ensures stable generation for indie developers building healthcare audio guides without unpredictable throttling during peak usage.
60 Requests Per Minute
Once your account is active, you can send up to 60 synthesis requests every 60 seconds. This throughput handles typical clinical text volumes efficiently, allowing you to generate patient guides or medical instructions at a steady pace.
Initial 10 RPM Limit
New accounts without a top-up start with a stricter limit of 10 requests per minute. This ensures system stability during your free trial phase. Once you add USDT credit (minimum $5), the limit automatically increases to the full 60 RPM.
Quota Monitoring
Track your usage directly on the dashboard. Each request consumes character units regardless of success, but failed synthesis returns the charge. Monitor your remaining balance and RPM status to avoid interruptions during high-volume medical content generation.
- Check balance and RPM on /get-api-key/
- Requests are processed sequentially under load
- Failed requests do not consume credit
Error Handling
The API returns standard HTTP status codes to indicate request outcomes, ensuring your healthcare application can programmatically handle failures. Understanding these codes helps you distinguish between client-side mistakes and server-side issues during audio generation.
Common errors include 400 Bad Request for malformed JSON, 401 Unauthorized for invalid keys, and 429 Too Many Requests when exceeding limits. Each response includes a clear message to aid debugging in your integration workflow.
Common HTTP Errors
Use 4xx codes for client issues like missing fields or invalid characters. 5xx codes indicate temporary server problems; retry with exponential backoff.
- 400: Invalid JSON structure
- 401: Invalid or expired API key
- 429: Rate limit exceeded
Invalid Input Text
Text exceeding 4096 characters returns a 400 error. Ensure your input text is within limits and properly encoded as UTF-8.
- Max 4096 characters per request
- Ensure valid UTF-8 encoding
- Check for unsupported special characters
Rate Limit Exceeded
Exceeding 60 requests per minute triggers a 429 error. Monitor your usage via the dashboard to avoid interruptions in service.
- 60 requests per minute per key
- 10 requests per minute before top-up
- Monitor usage in dashboard
Speed Control
The speed parameter lets you adjust voice tempo between 0.25 and 4.0, allowing precise control over how fast medical terms are delivered. This feature ensures your audio guides match the pacing required for patient comprehension or rapid clinical workflows.
Adjustable Speed 0.25-4.0
Set the speed value in your JSON body to slow down narration for complex instructions or speed it up for routine updates. The API accepts any float within this range, giving you granular control over the final audio output.
Impact on Generation
Adjusting speed directly affects generation time. While typical synthesis runs at roughly real-time speed (25 characters per second), slower speeds may take slightly longer, and faster speeds may process quicker. Requests are processed sequentially, so under load, queue times apply regardless of speed setting.
Clinical Speed Settings
For patient-facing guides, a speed of 0.8–1.0 often balances clarity with engagement. For internal clinical notes, speeds up to 2.0 can help providers digest information faster. Test specific medical terminology at different speeds to ensure pronunciation remains clear at higher tempos.
Language Settings
Specify the language explicitly using an ISO 639-1 code to ensure accurate pronunciation, especially for non-English Latin text. While the API guesses the language from the script, setting this field prevents errors in mixed-language medical texts.
Auto-detection works well for standard inputs, but for clinical terms or mixed scripts, manual override is recommended. This ensures that Hindi, Spanish, or other supported languages are rendered correctly without ambiguity.
ISO Code Input
Pass the language field in your JSON body with a two-letter ISO code (e.g., hi for Hindi, es for Spanish). This overrides any automatic detection and ensures the model uses the correct phonetic rules for your target language.
- Supported codes include: ar, zh, da, nl, en, fi, fr, de, el, he, hi, it, ja, ko, ms, no, pl, pt, ru, es, sw, sv, tr
Auto-Detection
If you omit the language field, the API attempts to infer it from the input text script. Latin script defaults to English, while Devanagari characters trigger Hindi processing.
- Detects based on character sets in the
inputtext.
Hindi Language Code
Use hi for Hindi. Any of the 8 voices can speak Hindi clearly. Ensure your text is properly encoded in UTF-8 to handle Devanagari characters correctly.
Model Versions
Choose between our standard and high-definition models based on your clinical audio needs. Both engines deliver clear, synthetic speech suitable for patient guides and medical instructions.
The choice affects audio fidelity but not your billing. Select the model that best matches your quality requirements for healthcare content.
tts-1 Standard
The tts-1 model provides efficient, clear audio synthesis. It is ideal for standard medical explanations and routine patient instructions where extreme fidelity is not critical.
- Fast generation times
- Clear articulation for general health info
- Standard audio quality
tts-1-hd High Quality
The tts-1-hd model offers enhanced audio fidelity. It is suitable for detailed medical terminology or sensitive patient communications where nuance matters.
- Higher audio resolution
- Better handling of complex terms
- Enhanced naturalness
Same Price Both
Both models cost the same: $10 per 1 million characters. You can switch between them per request without any price difference.
- No price premium for HD
- Uniform billing per character
- Switchable per API call
Text Input Limits
Each API call accepts up to 4096 characters, including spaces and punctuation. This limit ensures consistent processing speed and predictable billing for medical text generation.
4096 Characters Max
The input field caps at 4096 characters. Exceeding this limit returns an error. Short patient instructions or medication labels fit easily within this boundary.
- Spaces count as characters.
- Punctuation is included in the count.
- Limit applies per request, not per document.
Long Text Splitting
For longer clinical guides, split the text into chunks of 4096 characters or fewer. Generate audio for each chunk separately, then join the files. This maintains audio continuity and prevents request failures.
- Split at natural pause points.
- Avoid breaking mid-sentence.
- Join outputs sequentially.
Chunking Strategy
Use sentence boundaries or logical sections for splitting. This ensures the TTS engine maintains natural prosody between generated clips. For Hindi medical terms, ensure the language code is set consistently across all chunks.

Authentication
Authentication for the VoxCare TTS API relies on a single active bearer token per account. Include your key in the Authorization header as Bearer tts-... for every request to https://api.288t.info/v1.
Each account holds only one active key at a time. Issuing a new key immediately invalidates the previous one, ensuring simple, secure access without managing multiple tokens.
Bearer Token Auth
Pass your unique API key in the HTTP Authorization header using the Bearer scheme. The format is Authorization: Bearer tts-your_key_here. This token grants access to all endpoints, including speech generation and voice listings.
- Include
Authorization: Bearer tts-...in every request header. - Use the key issued on your /get-api-key/ dashboard.
- Only one key is active per account.
Key Rotation
Rotate keys by generating a new one from your dashboard. The old key stops working immediately upon creation of the new one. There is no overlap period, so ensure your application updates the header before the old key expires.
- Generate new key via dashboard.
- Old key invalidates instantly.
- Update header before old key expires.
Security Best Practices
Store your key in environment variables, not in client-side code. Since requests are processed server-side, hiding the key from end-users prevents unauthorized usage of your billing balance. Regenerate if suspected exposure.
- Use environment variables.
- Avoid client-side exposure.
- Regenerate on suspicion.
Webhook Support
VoxCare’s text-to-speech API is designed for synchronous, request-response workflows rather than asynchronous event delivery. When you send a synthesis request, the API processes your Hindi or English medical text and returns the audio file directly in the HTTP response body. This eliminates the need for background job tracking or complex state management, allowing your healthcare application to play audio immediately after generation.
No Webhooks Available
Our API does not support webhooks. You will not receive a POST notification when synthesis completes because the audio is delivered instantly within the same connection. This simplifies integration for indie developers who prefer predictable, linear API calls over managing incoming event endpoints.
Polling Method
Since asynchronous polling is unnecessary for our synchronous model, you do not need to poll for status updates. The response is either successful (200 OK) or an error. For long texts exceeding 4096 characters, your client must handle chunking and concatenation locally before or after receiving the individual audio segments.
- Use synchronous POST requests for immediate audio delivery
- Handle client-side chunking for texts over 4096 characters
- No status endpoints required for standard synthesis jobs
Sync Responses
Every request returns the audio file in the requested format (mp3, wav, opus, flac, or pcm) alongside metadata. This ensures that your healthcare application can cache the audio immediately. The synchronous nature guarantees that billing metadata is recorded simultaneously with audio generation, simplifying your cost tracking.
Examples
These examples demonstrate how the API handles medical terminology in Hindi, standard English instructions, and mixed-language inputs. Each snippet shows the specific JSON payload structure required for the POST /v1/audio/speech endpoint.
Use these templates as a starting point for integrating VoxCare into your healthcare applications. They highlight correct voice selection and language code usage for accurate synthesis.
Hindi Medical Term
Synthesizing medical terms in Hindi requires explicit language tagging to ensure accurate pronunciation. The following request uses the hi ISO code with the 'nova' voice, which provides a clear, bright tone suitable for patient guides.
- curl -X POST https://api.288t.info/v1/audio/speech \ -H 'Authorization: Bearer tts-...' \ -H 'Content-Type: application/json' \ -d '{"model": "tts-1", "input": "रक्तचाप की जाँच करें", "voice": "nova", "response_format": "mp3", "language": "hi"}'
English Instruction
For standard English instructions, such as those found in dosage guides, the API automatically detects the Latin script language if no language field is provided. This defaults to English, simplifying the payload for common use cases.
- curl -X POST https://api.288t.info/v1/audio/speech \ -H 'Authorization: Bearer tts-...' \ -H 'Content-Type: application/json' \ -d '{"model": "tts-1-hd", "input": "Take one tablet twice daily with food", "voice": "sage", "response_format": "wav"}'
Mixed Language
When your medical text contains both English and Hindi, such as transliterated drug names, explicitly setting the language field to hi ensures the engine prioritizes Hindi phonetics while handling English loanwords correctly. This prevents mispronunciation of mixed scripts.
FAQs
Developers often ask if Hindi text requires specific character encoding. The API accepts standard UTF-8 input, ensuring smooth handling of Devanagari script without additional conversion steps.
More Questions Below
You can generate audio for medical terminology in Hindi using any of the eight voices, as they all support all 23 languages. For longer patient guides, split your text into chunks under 4,096 characters and join the resulting audio files manually.
Failed requests incur no charge, but standard requests are billed immediately. Since processing is sequential, high-volume usage may experience slight queuing delays during peak times.
- Voices are preset; custom cloning is not available.
- No SSML or emotion tags are supported.
- Audio is not stored after generation.
Support
We prioritize developer efficiency with comprehensive documentation and direct email support. Our team reviews tickets promptly to resolve integration issues or billing questions without unnecessary delays.
Email Only
Send your queries to [email protected]. We handle all support via email to ensure detailed, searchable records for every technical or billing issue.
No Phone Support
We do not offer phone support. This keeps our operational costs low, allowing us to maintain transparent pricing for indie developers and healthcare apps.
Developer Docs
Our documentation covers Hindi text-to-speech specifics, voice selection, and error handling. Use the docs to integrate quickly and understand rate limits and character limits.
- Check /docs/ for API reference
- Review voice options for medical clarity
- Test with provided curl examples
Changelog
We continuously refine the VoxCare API to ensure reliable speech synthesis for medical texts. This changelog tracks updates to voice models, supported audio formats, and core API behaviors.
All changes are tested against Hindi and English medical terminology to maintain clarity and precision for indie healthcare developers.
API Updates
Standardized response headers for easier debugging in healthcare apps.
Improved error messages for invalid character limits.
- Updated /v1/audio/speech endpoint stability
- Refined rate limit handling for bulk requests
Voice Additions
No new voices added recently. The existing 8 presets remain the core offering.
All voices continue to support Hindi and 22 other languages.
Format Changes
Opus and FLAC formats are now fully supported for high-quality medical archives.
PCM raw audio remains available for low-level audio processing.
- Added Opus support
- Added FLAC support
Terms of Service
By using the VoxCare API, you agree to generate audio from text inputs solely for lawful purposes. You retain ownership of the generated audio files, but acknowledge that the underlying voice models are based on licensed recordings from LibriTTS-R and LibriVox public-domain sources.
You are responsible for ensuring your input text does not infringe on third-party rights. Since our voices are synthetic, you may use the output in commercial projects, including healthcare apps and patient guides, without additional licensing fees.
Usage Rights
You may use generated audio for internal, external, and commercial applications. The audio files are yours to distribute, embed in apps, or include in patient education materials. We do not claim ownership over your specific input text or the resulting audio files you create.
- Generate unlimited audio within rate limits.
- Distribute audio files in any format.
- Use audio in mobile or web apps.
Commercial Use
The API is available for commercial use without restriction. You can integrate the audio into paid healthcare products, educational platforms, or accessibility tools. There are no extra fees for commercial volume beyond the standard per-character pricing.
Attribution
While not strictly required, we appreciate attribution in your product documentation or about pages. You may credit 'VoxCare' or 'VoxCare API' as the text-to-speech provider. This helps other developers discover our service and supports our independent development.
Data Privacy
Your input text is used exclusively for generating the requested audio file and is not used for training our models. We do not retain your medical or patient guide text after synthesis is complete. Generated audio is returned directly in the response and is not stored on our servers, ensuring that sensitive healthcare data remains ephemeral. This approach minimizes exposure for indie developers building accessible health tech applications.
We maintain minimal request metadata—specifically timestamp, character count, and status—to facilitate accurate billing and usage tracking. This metadata does not include the actual text content or audio files. Since we do not store audio, you are responsible for archiving or discarding generated files according to your own compliance requirements.
No Training Data
Input text is used solely to produce the audio and is not used for training. We do not analyze your medical terms or patient instructions to improve our voice models. Your data remains yours, ensuring privacy for sensitive healthcare content without hidden usage for algorithmic improvement.
- Text is not used for model training
- No analysis of medical content for AI development
- Data remains isolated per request
No Audio Storage
Generated audio is returned in the response and not stored on our servers. Once the audio file is delivered to your application, we do not keep a copy. This ensures that your synthesized medical guides or patient instructions are not retained in our infrastructure, reducing your compliance burden.
- Audio is not stored after delivery
- No long-term audio archives
- Reduced storage compliance requirements
Metadata Retention
Request metadata (time, characters, status) is kept for billing purposes only. This limited data allows us to accurately charge your account based on the $0.01 per 1,000 characters rate. We do not store the content of the text or the resulting audio in these logs.
- Metadata kept for billing accuracy
- No content stored in logs
- Limited retention period for billing records
Contact
We prioritize developer needs with direct email support for technical and billing inquiries. Unlike traditional support models, we offer no phone numbers or live chat, ensuring your queries are handled asynchronously by our team.
Support Email
For general questions, documentation issues, or voice selection advice, email us at [email protected]. We aim to respond within one business day.
Developer Queries
Use the same email for technical questions about the API, rate limits, or integration issues. Include your request ID and error logs for faster resolution.
Billing Support
For TRC-20 top-up issues, balance discrepancies, or charge questions, contact [email protected]. Provide your account email and transaction hash for accurate tracking.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
