Frequently asked questions
What is real time text to speech?
Real-time text-to-speech synthesizes audio quickly enough for natural conversation flow. Our API delivers synthetic audio fast enough for IVR systems, avoiding the latency of legacy systems. The speed supports natural dialogue patterns for call centers and support bots.
How fast is the synthesis speed?
Typical speed is roughly real time, generating about 25 characters of text per second of audio. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins.
Can I use this for IVR systems?
Yes. We help product teams deploy text-to-speech for IVR and support bots without the latency of legacy systems. Our API delivers synthetic audio fast enough for natural conversation flow, making it suitable for call center environments requiring responsive audio responses.
What languages are supported?
We support 23 languages: 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. Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali and others are not supported.
How many characters per request?
Each request accepts up to 4096 characters of input text. For longer texts, you should split the content into parts of up to 4096 characters and join the resulting audio files. Spaces and punctuation count toward this character limit.
What audio formats are available?
You can choose from mp3, wav, opus, flac, and pcm formats. These options allow you to select the best balance of quality and file size for your IVR system or call center application needs.
Is there a free trial?
Yes, signing in with Google gives you $0.50 of credit (about 50,000 characters) valid for 7 days. Accounts created with email and password start without trial credit. This allows you to test the API before purchasing.
How does pricing work?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. You can top up with USDT (TRC-20) with a minimum of $5. There are no monthly plans, seats, or minimum spend requirements.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests, ensuring you only pay for successfully generated audio files. This protects your budget during testing or unexpected service interruptions.
Can I clone a custom voice?
No, we do not offer custom voice cloning. You cannot upload your own voice or design a custom voice. We provide eight preset voices based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings.
Do you support SSML?
No, we do not support SSML. There are no emotion tags, phoneme dictionaries, or custom pronunciation lexicons. The API accepts plain text input and uses the specified voice and speed parameters to generate the audio file.
Is there a mobile SDK?
No, we do not have an official mobile SDK. You can use the official OpenAI SDKs by changing the base URL to our API endpoint, or use plain HTTP requests. There is also no WordPress plugin or browser extension.
How do I handle long texts?
Split your text into parts of up to 4096 characters. Send each part as a separate request and join the resulting audio files. This ensures each request stays within the character limit and processes efficiently.
What is the latency like?
Typical speed is roughly real time (25 characters per second). Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. We help teams avoid legacy system latency.
First request
curl
curl https://api.0000ff.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 Speed Matters in IVR
In IVR systems, latency directly impacts user experience. Long wait times frustrate callers and increase abandonment rates. Our API generates synthetic audio quickly, ensuring that prompts play almost instantly after a request is sent.
Reducing Customer Wait Time
Standard TTS systems often introduce noticeable delays. Our cloud API delivers audio files rapidly, keeping the conversation flow natural. Callers hear responses without awkward pauses, improving satisfaction and reducing perceived wait times.
Handling Variable Load
Call centers experience fluctuating traffic. Our infrastructure processes requests sequentially but efficiently. Even under load, the system maintains consistent performance. You can scale usage without worrying about sudden spikes causing system failures.
Keeping Conversations Natural
Natural conversation requires timely responses. Our API supports speeds up to 4.0x, allowing for brisk, engaging interactions. Voices like Nova or Felix add energy to promotional calls, while Atlas provides clear, neutral tones for news updates.
How Our API Works
Our API accepts standard JSON payloads and returns synthesized audio files directly, streamlining the integration process for IVR systems. By sending a simple POST request with your text and voice preference, you receive an audio file ready for immediate playback in your call flow.
The endpoint mirrors the OpenAI speech API structure, allowing you to use existing OpenAI SDKs by simply updating the base URL. This compatibility reduces development time, as your team can leverage familiar tools and libraries to connect your call center software to our TTS engine without rewriting integration logic.
Simple JSON Integration
Sending text is straightforward: structure your request body with the model, input, voice, and response_format fields. The API validates the input and processes the synthesis, returning the audio file in your chosen format. This simplicity ensures that your IVR system can handle variable loads without complex middleware.
- Standard JSON request body
- Support for mp3, wav, opus, flac, and pcm
- Configurable speed between 0.25 and 4.0
OpenAI SDK Compatible
Since our endpoint matches the OpenAI speech schema, you can use the official OpenAI SDKs with minimal configuration. Just change the base_url to https://api.0000ff.info/v1 and provide your API key. This approach allows product teams to maintain existing codebases while switching to our engine.
Instant Audio Delivery
Audio files are generated and returned within the HTTP response, eliminating the need for polling or webhooks. (Note: generation takes time, so this is not instant streaming.) For typical texts, generation takes roughly 25 characters per second of audio. Short phrases return quickly, while longer texts are split into parts and joined seamlessly to maintain conversation flow.
Voices for Professional Environments
Select voices that match your brand’s tone while maintaining professional clarity for callers. Our library offers distinct presets designed for different interaction styles, ensuring your IVR sounds natural and consistent.
Clear Narrator Voices
Aria provides a warm, clear narration, and Luna offers a soft, storytelling tone. Sage offers a calm, instructional tone perfect for complex guidance.
Conversational Male Voices
Felix brings energetic energy for promotional messages, while Milo uses a friendly, conversational style for customer support interactions. Both ensure the caller feels heard.
Neutral News Style
Atlas delivers a neutral, news-like delivery for status updates, and Orion provides a deep, documentary style for premium service announcements. These voices remain authoritative yet approachable.
Supported Languages
Our API supports 23 languages, ensuring your IVR systems can reach a global audience without language barriers. Every voice can speak any of the supported languages, allowing you to maintain consistent audio quality across different regions.
Major Global Languages
We cover widely spoken languages, including English, Spanish, French, German, Italian, Portuguese, Russian, Japanese, Korean, and Chinese.
- English, Spanish, French, German, Italian, Portuguese, Russian, Japanese, Korean, Chinese
European Support
Beyond major languages, we support Danish, Dutch, Finnish, Greek, Hebrew, Polish, Swedish, and Turkish. This allows for localized customer service experiences across diverse markets.
- Danish, Dutch, Finnish, Greek, Hebrew, Polish, Swedish, Turkish
Asian Markets
We also support Arabic, Hindi, and Malay, enabling expansion into key Asian and Middle Eastern markets. Any voice can speak any of these languages.
Performance Metrics
Generating audio at roughly one second per 25 characters ensures synthetic voices feel natural during IVR interactions. Short phrases typically require only a few seconds, while longer texts maintain real-time pacing without awkward pauses.
Requests are processed sequentially, meaning heavy loads may introduce brief delays as your text moves through the generation queue. This linear processing ensures stable output.
Generation Speed
Synthesis averages approximately one second of audio per 25 characters of input text. This speed supports natural conversation flow for most standard IVR prompts, keeping hold music minimal and customer wait times low.
Queue Management
Since requests are processed one after another, high-volume bursts may result in temporary queuing. Under load, a request might wait briefly before synthesis begins, but this ensures stable, predictable output without dropping audio quality.
Request Limits
Each API key allows 60 requests per minute under normal operation. New accounts start with a lower limit of 10 requests per minute until the first top-up is processed. This structure prevents sudden spikes from overwhelming the generation engine.
- 60 requests/minute per key (standard)
- 10 requests/minute (pre-top-up)
- Sequential processing ensures stability

Technical Requirements
Our API enforces strict technical boundaries to ensure reliable synthesis. Understanding these limits helps you design robust IVR flows that avoid errors and maintain call quality.
Inputs are capped at 4096 characters per request. For longer prompts, split the text and join the resulting audio files to preserve natural conversation flow.
Character Limits
Each request accepts up to 4096 characters, including spaces and punctuation. Exceeding this limit returns an error; split long scripts into smaller segments before sending.
Audio Formats
We support MP3, WAV, Opus, FLAC, and PCM. For IVR systems, MP3 or Opus offers a good balance of quality and bandwidth efficiency.
All files include an inaudible watermark identifying them as synthetic speech, which may be required by your telephony provider.
Bandwidth Considerations
Generation typically takes about 25 characters per second. Plan your telephony wait times accordingly to avoid premature timeouts.
Under load, requests queue sequentially. Monitor your usage to ensure sufficient throughput during peak call volumes.
Integration Examples
Integrating our TTS API into your IVR system is straightforward, whether you prefer raw HTTP requests or a dedicated SDK. You can generate audio files instantly by sending a simple POST request with your text and voice preference.
Our API mirrors the OpenAI speech endpoint structure, allowing you to reuse existing client libraries by simply adjusting the base URL. This compatibility allows teams already familiar with modern TTS workflows to integrate easily.
curl Command
Use this command to test the endpoint directly from your terminal. Replace YOUR_API_KEY with your key from /get-api-key/.
```bash curl -X POST "https://api.0000ff.info/v1/audio/speech" \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d "{\"model\": \"tts-1\", \"input\": \"Welcome to support, please hold.\", \"voice\": \"sage\", \"response_format\": \"mp3\"}" \ --output audio.mp3 ```
- Ensure your API key is valid and has sufficient balance.
- The response body contains the raw audio binary data.
Python SDK Setup
Install the OpenAI Python package, which works seamlessly with our API by pointing it to our base URL.
```python import openai client = openai.OpenAI(base_url="https://api.0000ff.info/v1", api_key="YOUR_API_KEY") speech_file = client.audio.speech.create( model="tts-1", voice="nova", input="Hello, how can I help you?" ).content ```
- Set
base_urltohttps://api.0000ff.info/v1. - Use
tts-1ortts-1-hdas the model ID.
Node.js Implementation
For JavaScript environments, use the official OpenAI Node.js package. Configure the client to use our API endpoint.
```javascript import OpenAI from 'openai'; const client = new OpenAI({ baseURL: 'https://api.0000ff.info/v1', apiKey: 'YOUR_API_KEY' }); const mp3 = await client.audio.speech.create({ model: 'tts-1', voice: 'aria', input: 'Your call is important to us.' }); ```
- Initialize the client with the custom base URL.
- Handle the audio stream or buffer as needed for your IVR logic.
Pricing Overview
Our pricing model is straightforward: $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, ensuring you only pay for successful audio generation.
Pay Per Character
You are charged based on the input text length. With a typical speed of roughly 25 characters per second, long IVR menus generate audio in near real-time. You can process texts up to 4,096 characters per request.
Trial Credit
Sign in with Google to receive $0.50 in free trial credit, valid for 7 days. This allows you to test up to 50,000 characters. Email-based accounts start without trial credit.
No Hidden Fees
We do not offer monthly plans, seats, or subscriptions. Payments are made via USDT (TRC-20) on the TRON network. There are no invoices, VAT, or minimum spend requirements. Your balance never expires.
- No monthly plans or seats
- USDT (TRC-20) payments only
- No minimum spend
- Balance does not expire
Get Started
Start with a $0.50 trial valid for 7 days. This gives you 50,000 characters to test latency and quality without entering payment details.
Create your account on the /get-api-key/ page. You can sign in with Google or use a standard email and password.
Sign Up for Trial
Visit the registration page and choose Google or email sign-up. Google accounts receive an immediate $0.50 credit. Email-based accounts start with zero balance.
- Google sign-up includes free trial credit
- Email sign-up requires immediate top-up
- No credit card required to start
Generate API Key
Your dashboard displays your unique Bearer token immediately. This key authenticates all requests to the API endpoint.
- One active key per account
- Issue a new key anytime
- Old key stops instantly
First Request
Send a POST request to /v1/audio/speech with your text and selected voice. Use the tts-1 model for standard speed or tts-1-hd for higher quality.
- Max 4096 characters per request
- Supports mp3, wav, opus, flac, pcm
- Rate limit: 60 requests per minute
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This model scales naturally with your call volume, whether you handle a few hundred or millions of interactions monthly.
23 languages
Any voice speaks any of these languages.
