Frequently asked questions
What is TTS MP3?
TTS MP3 is an audio file generated by converting text into speech via the SpokenWave API. The service accepts text input and returns compressed MP3 audio, suitable for advertising and radio spots. The audio is synthetic, marked with an inaudible watermark, and delivered via a standard REST endpoint compatible with common SDKs.
How does the TTS API work?
Send a POST request to the /v1/audio/speech endpoint with your text, voice selection, and format preferences. The API processes the text and returns the audio file. You can use the OpenAI SDK by changing the base URL. Input is limited to 4096 characters per request, with longer texts requiring manual splitting.
Which voices are available for advertising?
Eight presets are available, including Felix (energetic, promo) and Milo (friendly, conversational), ideal for advertising. Other options include Aria, Nova, Luna, Sage, Atlas, and Orion. Each voice can speak any supported language. You select the voice via the voice parameter in your API request.
What languages are supported?
The API supports 23 languages, including English, German, Spanish, French, Japanese, and Arabic. Any voice can speak any of these languages. If the language field is omitted, the system guesses the language, defaulting to English for Latin script. Vietnamese, Thai, and Ukrainian are not supported.
How much does the API cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full. There are no monthly plans, seats, or minimum spends. Balance does not expire.
Is there a free trial?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This covers approximately 50,000 characters. Accounts created with email and password do not receive trial credit. Top-ups are available via USDT on the TRON network.
Can I use the OpenAI SDK?
Yes, the API request shape matches the OpenAI speech endpoint. You can use the official OpenAI SDKs by setting the base_url to https://api.playgo90.com/v1 and using your SpokenWave API key. No custom SDK is required.
What audio formats are supported?
The API supports MP3, WAV, OPUS, FLAC, and PCM formats. You specify the desired format using the response_format parameter in your request. MP3 and WAV are standard for advertising workflows, while FLAC offers lossless quality.
How fast is the generation?
Generation is roughly real-time on long texts, processing about 25 characters per second. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is suitable for batch advertising spot creation.
Do I need to pay for failed requests?
No, failed requests are free. If synthesis fails, the charge is returned in full. You are only charged for successful audio generation. This applies to all requests processed by the API.
How do I integrate the API?
Send a POST request to https://api.playgo90.com/v1/audio/speech with a JSON body containing model, input, voice, and response_format. Authenticate using Authorization: Bearer tts-.... You can use the OpenAI SDK by adjusting the base URL or send plain HTTP requests.
Are the voices licensed?
Yes, voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark marking it as synthetic speech. No custom voice cloning is offered.
Can I control the speed of the speech?
Yes, you can adjust the speech speed between 0.25 and 4.0 using the speed parameter. This allows you to speed up or slow down the generated audio to fit specific advertising timing requirements or brand voice styles.
How do I contact support?
Support is available via email only. There is no phone number, live chat, or SLA. For issues regarding your API key, billing, or technical questions, send an email to the support address provided on the contact page.
First request
curl
curl https://api.playgo90.com/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.mp3How it works
Send text to our REST endpoint and receive an audio file. The API accepts JSON requests and returns synthesized speech in standard formats. This simple workflow integrates directly into your content production pipeline without requiring complex middleware.
Simple REST endpoint
Use a single POST request to generate audio. The endpoint accepts your text input and parameters, returning the audio file directly in the response. This reduces integration time and keeps your ad production workflow streamlined.
- POST to /v1/audio/speech
- JSON request body
- Direct audio file response
OpenAI SDK compatible
Our API follows the same request shape as the OpenAI speech endpoint. You can use official OpenAI SDKs by changing the base_url to https://api.playgo90.com/v1. This allows for quick adoption using tools your developers already know.
- Compatible with OpenAI SDKs
- Change base_url only
- Standard request structure
Multiple audio formats
Select the output format that fits your broadcast needs. We support MP3, WAV, OPUS, FLAC, and PCM. This flexibility ensures compatibility with various advertising platforms and radio station delivery standards.
- MP3, WAV, OPUS, FLAC, PCM
Voices for your brand
Select from eight distinct voice presets to match your brand’s identity. Each voice has a specific preset style, ensuring consistent tone across your advertising campaigns and radio spots.
Our library includes four female and four male options, ranging from warm narrators to energetic promo voices. Any voice can speak any of the 23 supported languages, allowing for flexible localization.
Female presets ['Aria offers a warm, clear narration style suitable for brand stories. Nova provides a bright, upbeat tone ideal for promotional content. Luna delivers a soft, storytelling voice for narrative ads. Sage presents a calm, instructional tone for explanatory spots.', 'Each female voice maintains consistent emotional neutrality while delivering high clarity. These presets are suitable for short-form advertising where clarity is critical.', 'Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. This ensures legal clarity for commercial use without additional royalty burdens.']
Male presets ['Felix brings an energetic, promo-ready voice for high-impact advertisements. Milo offers a friendly, conversational tone for customer-facing content. Atlas provides a neutral, news-style delivery for informative spots. Orion delivers a deep, documentary voice for authoritative branding.', 'These male voices are designed for clarity and professional appeal.', 'Like the female presets, these are based on licensed recordings from LibriTTS-R (CC BY 4.0), ensuring consistent quality and legal compliance for commercial advertising applications.']
Licensed recordings ['All voices are derived from licensed recordings available under CC BY 4.0. This licensing model applies to the source recordings.', 'Each generated audio file includes an inaudible watermark marking it as synthetic speech. This helps identify AI-generated content while maintaining the professional quality expected in broadcast media.'] ['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']
Supported languages
SpokenWave supports 23 languages, covering major markets for advertising and radio. The service handles diverse scripts, ensuring clear pronunciation for global campaigns.
23 languages available
The API supports 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, allowing flexible casting for international spots.
Automatic language detection
If the language field is omitted, the system guesses the language from the text script. Latin script text defaults to English. This simplifies integration for primary English-language radio ads.
Manual language override
For non-English Latin-script text, set the language parameter explicitly to ensure correct pronunciation. This prevents the default English reading of words like "café" or "naïve" in French or Spanish copy.
- Not supported: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali, and all others not listed above.
Pricing model
SpokenWave charges $0.01 per 1,000 characters, including spaces and punctuation. Each request costs $10 per million characters processed. Failed synthesis requests are free, with charges returned in full if the audio generation fails.
Top-ups are made via USDT (TRC-20) on the TRON network, with a minimum deposit of $5. Balances do not expire, and there are no monthly subscriptions, seats, or minimum spend requirements.
Pay per character
Usage is billed strictly by character count. The rate is $10 per 1 million characters, equating to $0.01 per 1,000 characters. This model ensures you only pay for the audio actually generated.
- Rate: $10 per 1,000,000 characters
- Cost: $0.01 per 1,000 characters
- Includes spaces and punctuation in count
No monthly fees
There are no recurring subscription costs or minimum commitments. You can top up your balance as needed and use it at your own pace. The balance remains available until exhausted.
- No monthly plans
- No seats or per-user fees
- Balance does not expire
Free trial credit
Signing in with Google provides $0.50 in trial credit, valid for 7 days. This covers approximately 50,000 characters. Accounts created with email and password do not receive trial credit.
- Trial credit: $0.50
- Valid for 7 days
- Requires Google sign-in
Technical specifications
SpokenWave is engineered for consistent API performance, with clear constraints on request volume, text size, and playback speed to ensure predictable generation times for advertising workflows.
Rate limits
API keys are limited to 60 requests per minute. New accounts start with a lower threshold of 10 requests per minute until the first top-up is processed.
Input text length
Each request accepts up to 4096 characters of input text. Longer scripts should be split into segments and joined during playback.
Speed control
The speed parameter accepts values between 0.25 and 4.0, allowing precise adjustment of voice pacing. Typical generation speed is roughly real-time, at approximately 25 characters per second.

Audio quality
SpokenWave delivers consistent audio quality optimized for advertising and radio spots. Each generated file carries an inaudible watermark that marks it as synthetic speech. The service maintains a steady tone across all voices, suitable for professional brand voices.
Generation speed is roughly real-time, processing approximately 25 characters per second. While requests are processed sequentially, short phrases complete quickly. Longer texts are split into parts and joined during playback.
Synthetic watermark
Every audio file includes an inaudible digital watermark marking it as synthetic speech. This ensures clear identification of generated content for broadcast standards.
The watermark is embedded during synthesis and does not affect audio fidelity or playback quality in standard players.
- Inaudible to human listeners
- Embedded in all formats (mp3, wav, opus, flac, pcm)
- Marks synthetic origin for compliance
Real-time generation
Text is converted to audio at roughly real-time speed. Short phrases take a few seconds to generate. Longer texts are processed in parts and joined automatically.
Requests are processed sequentially. Under normal load, generation time matches text length closely. High volume may introduce brief queue delays.
- ~25 characters per second generation rate
- Automatic splitting for texts over 4096 characters
- Sequential processing ensures consistency
Consistent tone
Voices provide stable, professional tones suitable for advertising. Each preset maintains a consistent tone across different texts.
No dynamic emotion tags or SSML are used. Tone is determined by the selected voice preset, ensuring predictable results for repeated spot variations.
- Fixed voice characteristics per preset
- No dynamic emotion modulation
- Consistent output for branding
Integration options
Integrate SpokenWave into your advertising workflow using standard HTTP requests or familiar SDKs. The API mirrors the OpenAI speech endpoint structure, allowing you to switch bases without rewriting core logic. This compatibility ensures rapid deployment for startups building automated ad production pipelines.
cURL example
Use cURL for quick testing or lightweight integrations. The following command sends a text payload to the speech endpoint and saves the audio output.
- Endpoint: POST https://api.playgo90.com/v1/audio/speech
- Auth: Bearer tts-<your-key>
- Body: JSON with model, input, voice, and response_format
Python SDK
Leverage the official OpenAI Python SDK by updating the base URL. This approach maintains type safety and error handling while using SpokenWave’s engine for ad spot generation.
- Install: pip install openai
- Set base_url to https://api.playgo90.com/v1
- Use client.audio.speech.create() method
JavaScript SDK
Integrate directly into web applications or Node.js services. The same request shape used by the OpenAI SDK works seamlessly, enabling dynamic audio generation for interactive ad campaigns.
- Install: npm install openai
- Configure base_url to https://api.playgo90.com/v1
- Call speech.create() with voice and input parameters
Use cases
SpokenWave enables startups to produce professional advertising audio without studio overhead. By sending a simple text payload to the REST endpoint, teams generate broadcast-ready MP3 or WAV files in seconds, maintaining consistent tone across multiple campaigns.
The API handles character limits and formatting, allowing rapid iteration of radio spots. Teams can adjust voice presets and speed to match brand guidelines, ensuring every asset meets commercial standards before delivery.
Radio spots
Generate concise 15–30 second advertisements using presets like Felix for energetic promos or Atlas for neutral news-style reads. The API returns standard audio formats compatible with various platforms.
- Supports up to 4096 characters per request
- Output formats include MP3 and WAV for broad compatibility
- Speed adjustable from 0.25x to 4.0x for pacing control
Podcast intros
Create consistent brand signatures for podcast series using warm female voices like Aria or soft tones like Luna. Automated generation ensures every episode starts with identical audio quality, reinforcing brand recognition without manual recording sessions.
- Ideal for short, repeated segments
- Compatible with standard audio editing workflows
- No subscription fees per episode
IVR systems
Deploy clear, instructional voice menus for customer service lines using Sage or Milo. The API is suitable for interactive voice response systems where clarity is critical.
- Supports multiple languages for international support
- Requests are processed sequentially; latency varies with load.
- Cost-effective for high-volume automated calls
Support and contact
Support is provided via email only; there is no phone number or live chat available. The documentation is hosted at /docs/ and includes the full API reference and integration guides.
API status is not guaranteed by an SLA. Requests are processed sequentially, so queue times may occur during high load. Check the documentation for current limits and behavior.
Email support
Send inquiries to the support email address. Response times vary based on volume. Include your API key and request details for faster resolution.
Documentation
The technical documentation is available at /docs/. It covers endpoints, parameters, and examples for cURL, Python, and JavaScript.
- API reference
- Integration guides
- Error codes
API status
Uptime is not guaranteed. There is no enterprise SLA. Requests are queued if the server is busy.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Launch your startup with clarity, capturing attention instantly through compelling audio storytelling that resonates deeply with your target audience.
23 languages
Any voice speaks any of these languages.
