Frequently asked questions
What is the cost per character for this TTS API?
The cost is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, with charges returned in full if synthesis fails. There are no monthly plans, seats, or minimum spend requirements.
Does the API charge for failed requests?
No. If synthesis fails, the charge is returned in full. You only pay for successfully generated audio files. This ensures you are not billed for errors or processing issues during your integration workflow.
How many languages are supported?
The API supports 23 languages, including English, Spanish, French, German, Japanese, and Chinese. Any voice can speak any of these languages. If the language is not set, it is guessed from the script, defaulting to English for Latin text.
Can I use the OpenAI SDK with this API?
Yes. The endpoint shape matches the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.crn77.info/v1 and providing your site-specific key. This allows for rapid prototyping with existing code.
What payment methods are accepted?
We accept USDT on the TRON network (TRC-20) only. There are no cards, PayPal, subscriptions, or invoices with VAT. Top-ups are credited automatically within minutes. The minimum top-up amount is $5.
Is there a free trial available?
Yes, accounts signed in with Google receive $0.50 of credit (about 50,000 characters) valid for 7 days. Accounts created with email and password start without trial credit. The balance does not expire.
How fast is the text-to-speech generation?
Typical speed is roughly real time, processing about 25 characters of text per second of generation. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue.
Are the voices cloned from real people?
Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. They are not custom voice clones. Every generated file carries an inaudible watermark marking it as synthetic speech.
Do I need to pay for a monthly subscription?
No. There are no monthly plans, seats, or minimum spend requirements. You pay only for the characters you use. You can top up your balance with USDT whenever needed, and the balance never expires.
What is the character limit per request?
Each request supports up to 4096 characters of input text. For longer texts, you should split the text into parts of this size and join the resulting audio files. Spaces and punctuation count toward this limit.
Is my input text used to train models?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Only request metadata is kept for billing purposes.
Can I stream audio in real-time?
No. The API returns the complete audio file in the response. There is no streaming, WebSocket, or real-time partial audio support.
Does the API support SSML tags?
No. The API does not support SSML, phoneme dictionaries, custom pronunciation lexicons, or emotion tags. It accepts plain text input with parameters for voice, speed, and language.
How do I top up my balance?
Send USDT on the TRON network (TRC-20) to the provided address. The minimum top-up is $5. Credits are added automatically within minutes after the transfer is confirmed. No manual invoices or support tickets are required.
First request
curl
curl https://api.crn77.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.mp3Transparent Pricing Model
VoiceCoda bills strictly on a per-character basis at $10 per 1 million characters. This means you pay $0.01 for every 1,000 characters processed, including spaces and punctuation. There are no hidden fees, tiered volume discounts, or complex enterprise contracts to navigate. You only pay for what you actually use, making cost estimation straightforward for any project scale.
Unlike traditional TTS services that require monthly subscriptions or seat licenses, our model eliminates recurring fixed costs. Whether you generate ten lines of dialogue or ten thousand, the rate remains constant. This transparency allows indie developers to calculate exact integration costs upfront without worrying about unexpected overages or minimum spend requirements.
Per-character billing structure
Billing is calculated purely on character count. Spaces and punctuation count as characters. The rate is $10 per 1 million characters ($0.01 per 1,000 characters).
You can estimate costs by counting characters in your script. For example, a 4,000-character script costs $0.04. This linear pricing ensures predictability for budgeting.
- $10 per 1 million characters
- $0.01 per 1,000 characters
- Spaces and punctuation count
No minimum spend requirements
There is no minimum spend to start using the API. You can top up with as little as $5 using USDT (TRC-20).
This structure suits freelancers and small projects that may have variable usage patterns. You only fund what you need, avoiding tied-up capital.
Failed request credits
If a synthesis request fails, the charge is returned in full. You are not billed for audio files that are not successfully generated.
This protects your budget against network issues or invalid parameters. You only pay for successful audio outputs.
Integration for Developers
VoiceCoda uses the exact same request shape as the OpenAI speech endpoint, allowing indie developers to drop it into existing codebases with minimal changes. By simply adjusting the base_url to https://api.crn77.info/v1, you can leverage official OpenAI SDKs without writing custom HTTP clients.
Standard JSON endpoints streamline integration for freelancers building rapid prototypes or production apps. You send a POST request with your text and voice selection, receiving a direct audio file response. This eliminates the need for complex middleware or proprietary wrappers, keeping your architecture lean and transparent.
OpenAI SDK compatibility
Use the official OpenAI SDKs by pointing them to our base URL. This ensures you get standard error handling and retry logic without reinventing the wheel.
Your existing API key format works seamlessly. Just replace the base URL in your client configuration.
- Compatible with official OpenAI SDKs
- Simple base_url replacement
- Standard error structures
Standard JSON endpoints
The POST endpoint accepts JSON bodies with fields like model, input, voice, and response_format. This consistency makes debugging straightforward and predictable for developers familiar with RESTful APIs.
You can also query available voices and models via GET endpoints to dynamically update your application's UI based on current inventory.
Rapid prototyping workflow
Start with the free trial credit to test integration immediately. Generate audio files in seconds for short phrases, or batch longer texts by splitting them into 4096-character chunks.
Use the provided curl example to verify connectivity before integrating into your main codebase. This reduces integration friction for indie developers and freelancers who need to move fast.
Voice Options and Formats
Select from eight distinct voice presets tailored for specific tones, ranging from warm narrators to deep documentary styles. Each voice is derived from licensed recordings and supports clear, natural speech without the need for complex SSML or phoneme dictionaries.
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 character, from energetic promos to calm instructional tones, allowing you to match the audio to your project's mood instantly.
- 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
Multi-language support (23 languages)
All eight voices can speak any of the 23 supported languages, including English, Spanish, German, Japanese, and Arabic. You can specify the language via an ISO code or let the API guess it based on the input script, though setting it explicitly is recommended for non-English Latin text.
Audio formats: MP3, WAV, OPUS, FLAC, PCM
Generate audio in MP3, WAV, OPUS, FLAC, or PCM formats to suit your bandwidth and quality needs. Each generated file includes an inaudible watermark identifying it as synthetic speech, ensuring transparency without affecting playback quality.
Payment and Billing
We process payments exclusively via USDT on the TRON network (TRC-20). Top-ups start at a $5 minimum and are credited automatically within minutes of transfer. This streamlined method minimizes billing delays, ensuring your API access remains uninterrupted.
We do not store credit cards or accept PayPal. There are no recurring subscriptions, monthly plans, or VAT invoices. You pay only for the characters you consume, with no hidden fees or minimum spend requirements.
USDT (TRC-20) top-ups only
All top-ups are processed via USDT on the TRON network (TRC-20). The minimum top-up amount is $5, and funds are credited automatically within minutes of the transfer confirmation. This direct blockchain approach ensures quick availability for your projects.
There are no recurring subscriptions or monthly plans. You simply add funds as needed. The balance covers your usage at $0.01 per 1,000 characters, with no minimum spend requirements or hidden transaction fees.
- Minimum top-up: $5
- Network: USDT (TRC-20)
- Credit time: ~minutes
- No recurring subscriptions
No credit cards or PayPal
We do not store credit card details or accept PayPal. This keeps billing simple for indie developers. You avoid the complexity of recurring billing cycles or unexpected subscription renewals.
There are no invoices with VAT. You manage your own budget by topping up your account directly. This model is ideal for freelancers and small teams who prefer transparent, per-character billing without enterprise-level financial overhead.
Balance never expires
Your account balance does not expire. You can top up once and use the credits whenever you need them, whether for a short prototyping phase or long-term production. This eliminates the pressure to burn through credits before a deadline.
Failed requests are refunded in full, ensuring you only pay for successful audio generation. This protects your budget during testing phases where you might experiment with different voices or formats.
- Balance never expires
- No subscription deadlines
- Refunds for failed requests
Performance Limits
Understanding the operational limits of the VoiceCoda API is critical for indie developers planning their integration architecture. Our system processes requests sequentially, meaning that burst traffic may encounter brief queuing delays during high-load periods. These constraints are designed to maintain stable generation quality without requiring complex enterprise-grade infrastructure.
We enforce a strict input limit of 4,096 characters per request to ensure consistent processing times. For longer narratives, you must split the text and join the resulting audio files in your own code. This approach keeps individual API calls lightweight and predictable for rapid prototyping.
60 requests per minute limit
Each API key is capped at 60 requests per minute. Before your first top-up, this limit is reduced to 10 requests per minute to prevent abuse during the free trial period. Once you top up via USDT, the full rate limit is restored immediately.
Since requests are processed sequentially, exceeding this limit or having many concurrent long-generation jobs may cause your requests to wait in a queue. Plan your batch processing accordingly to avoid unnecessary delays in your pipeline.
- Standard limit: 60 requests/minute per key
- Trial limit: 10 requests/minute
- Sequential processing may cause queuing under load
4096 character input cap
The API accepts up to 4,096 characters of input text per single request. Spaces and punctuation count toward this limit. If your script exceeds this length, you must split the text into smaller chunks, generate audio for each, and concatenate the files.
This constraint simplifies the API design and ensures consistent performance. It also means you have full control over how long audio segments are, allowing you to optimize buffering for your specific application needs.
- Max input: 4,096 characters per request
- Spaces and punctuation count as characters
- Split and join logic required for longer texts
Real-time synthesis speed
Synthesis typically runs at roughly real-time speed, generating approximately 25 characters of text per second of audio. Short phrases may take a few seconds due to overhead, while longer texts process more efficiently.
This speed is sufficient for most indie projects, such as game dialogue or video voiceovers. However, keep in mind that under heavy load, request processing may slow down as jobs queue up behind previous submissions.
- Approx. 25 characters of text per second of audio
- Short phrases may take a few seconds
- Speed may vary under high load

Data Privacy
Your input text is processed solely to generate the requested audio file and is never retained for model training. This ensures that your specific narrative content remains private and is not used to improve the underlying TTS engine over time.
After the audio stream is returned in the response, the generated file is not stored on our servers. We retain only request metadata—such as timestamp, character count, and status—for accurate billing and usage tracking.
Input text not used for training
The text you send via the API is used exclusively for synthesis. Unlike many consumer-grade services, we do not collect your input data to train or refine our voice models, keeping your creative content isolated.
No audio storage after response
Generated audio is delivered directly in the API response and is not persisted in our storage systems. This minimizes data exposure and ensures that your voiceovers or game dialogues are not archived without your explicit action.
We keep only the metadata required for billing transparency: request time, character count, and success status. No audio files are kept for auditing or quality review after delivery.
Synthetic speech watermarking
Every audio file generated by VoiceCoda contains an inaudible digital watermark. This marker identifies the file as synthetic speech, helping platforms and users distinguish AI-generated audio from human recordings without affecting playback quality.
This watermark is embedded during synthesis and cannot be easily removed, providing a clear audit trail for content authenticity without adding noticeable latency or file size overhead.
Ideal Use Cases
VoiceCoda enables indie developers to integrate high-quality narration directly into game engines or freelance projects without complex enterprise contracts. By calculating exact costs per character, you can budget precisely for dynamic dialogue or static voiceovers, avoiding hidden fees common in larger platforms.
Indie game narration
Generate character dialogue or environmental narration on-demand using our 8 voice presets. With a 4096 character input cap per request, you can batch script lines efficiently. Every generated file carries an inaudible watermark marking it as synthetic speech.
- Supports 23 languages for localized game releases
- MP3 and WAV formats for easy engine import
- No minimum spend allows testing small dialogue sets
Freelance video voiceovers
Produce professional-grade voiceovers for YouTube, tutorials, or client presentations. Select from distinct voices like Aria or Orion to match your video’s style. Since input text is not used for training, your scripts remain private, and failed synthesis requests are refunded immediately.
- Choose from 8 licensed voice presets
- Transparent billing: $0.01 per 1,000 characters
- No SSML needed for basic emphasis
Automated voice responses
Integrate TTS into IVR systems or chatbots using standard JSON endpoints. The API accepts text and returns audio files, supporting formats like OPUS for efficient bandwidth usage. With 60 requests per minute, you can handle moderate traffic volumes.
- OpenAI SDK compatible for easy integration
- USDT (TRC-20) payments simplify cross-border billing
- Balance never expires for long-term projects
Getting Started
Start by creating an account at /get-api-key/ using your Google sign-in. This grants $0.50 in trial credit (approx. 50,000 characters) valid for 7 days, allowing immediate testing without payment setup.
Google sign-in for trial credit
Signing in via Google instantly provisions your account and credits $0.50. This trial is valid for 7 days, giving you 50,000 characters to test the API without entering payment details.
API key generation
Your dashboard displays your unique API key and current balance. You can generate a new key at any time; the previous key stops working immediately, ensuring secure access for your indie projects.
- Auth header: Authorization: Bearer tts-...
First curl request
Use the standard OpenAI-compatible endpoint. Send a POST request to https://api.crn77.info/v1/audio/speech with your JSON body. The response returns the audio file directly, ready for integration.
Example: curl -X POST https://api.crn77.info/v1/audio/speech -H "Authorization: Bearer YOUR_KEY" -d '{"model": "tts-1", "input": "Hello world", "voice": "nova", "response_format": "mp3"}'
Comparison to Enterprise Solutions
Enterprise TTS solutions often bundle complex tier structures with hidden usage caps, making budget forecasting difficult for small teams. VoiceCoda uses a flat per-character rate ($0.01 per 1,000 characters) with no minimum spend or seat limits, allowing precise cost calculation from day one.
Simpler pricing tiers
Unlike multi-tier enterprise plans that vary price by volume or feature access, our model scales linearly. You pay exactly for what you generate, eliminating surprise overage charges common in traditional API contracts.
No enterprise contracts
There are no monthly subscriptions, SLA guarantees, or complex legal agreements. Accounts are independent, and you can stop using the service at any time without penalty or invoice processing delays.
Direct developer support
Support is by email only. We skip the phone trees and live chat queues, providing direct, written assistance for technical integration issues without the overhead of enterprise customer success teams.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Spaces between words and punctuation marks like commas, periods, and question marks are included in the character count.
23 languages
Any voice speaks any of these languages.
