Frequently asked questions
What is TTS?
Text-to-speech (TTS) is a cloud API that converts written text into audio files. You send a POST request to our endpoint with your script, and receive an audio file in return. It is a RESTful service compatible with standard SDKs, designed for automated audio generation without human voice actors.
How does TTS work?
You send text via a JSON body to our API endpoint. The system processes the request using one of eight voice presets and returns an audio file. For texts over 4096 characters, you split the input and join the resulting audio files. The service handles synthesis via a simple REST call.
Is TTS good for ads?
Yes, SpokenWave offers voices like Felix for energetic promos and Milo for conversational spots. Our API allows rapid generation of advertising scripts in multiple formats. This enables startups to produce radio spots efficiently without booking studio time or hiring voice talent for every campaign variation.
How much does TTS cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Failed requests are free. You can start with a $0.50 trial credit. Top-ups are made via USDT on the TRON network. There are no monthly plans or minimum spend requirements.
Can I use TTS for radio?
Yes. You can generate audio files in MP3, WAV, Opus, FLAC, or PCM formats suitable for radio broadcasting. The API supports speeds from 0.25x to 4.0x, allowing you to adjust pacing for standard radio spot durations. The output is a standard audio file ready for transmission.
What languages does TTS support?
We support 23 languages including English, German, Spanish, French, Japanese, and Arabic. Any voice can speak any supported language. If the language is not specified, it is guessed from the script. Vietnamese, Indonesian, Thai, and Ukrainian are not supported.
Are the voices realistic?
Voices are based on licensed recordings from LibriTTS-R and LibriVox. They include presets like Aria for narrators and Atlas for news. Every generated file carries an inaudible watermark marking it as synthetic speech. They are realistic but identifiable as machine-generated audio.
Can I customize the voice?
You cannot customize the voice or clone your own. You choose from eight presets: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, or Orion. You can adjust the speed between 0.25 and 4.0. No SSML, emotion tags, or custom pronunciation lexicons are available.
How long does generation take?
Generation is roughly real-time, producing about 25 characters of text per second. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed matches real-time audio duration for long texts.
Do I need a developer?
A developer is helpful but not strictly required. The API uses a standard JSON body similar to OpenAI’s format. You can use the official OpenAI SDKs by changing the base URL. We provide a ready curl example on the dashboard for immediate integration.
Is TTS legal for ads?
Yes. Input text is used only to produce audio and is not used for training. Generated audio is returned in the response and not stored. The voices are based on licensed or public-domain recordings.
Can I use TTS commercially?
Yes. SpokenWave is a cloud API for startups creating advertising and radio spots. You pay per character used. The service is designed for business workflows, allowing you to generate unlimited audio files for your products or services.
What is the difference between TTS and voice acting?
TTS uses synthetic voices based on licensed recordings, while voice acting involves human performers. TTS is faster and cheaper, costing $0.01 per 1,000 characters. It lacks human nuance but offers consistency. You cannot clone specific human voices or add custom emotions with TTS.
How do I integrate TTS into my workflow?
Send a POST request to https://api.playgo90.com/v1/audio/speech with your text, voice, and format. Use your API key for authentication. You can use standard HTTP libraries or the OpenAI SDK. For long texts, split into 4096-character chunks and join the resulting audio files.
Definition
SpokenWave converts written text into audio files via a cloud API. Advertisers send a text payload to the endpoint and receive a processed audio file ready for broadcast. This method eliminates the need for studio booking and human voice talent for standard spots.
The MP3 format is the industry standard for digital and radio delivery. It provides consistent compression with minimal file size, ensuring fast loading times for web ads and reliable playback across all radio broadcasting systems.
Text to speech explained
The system accepts text input and generates speech using preset voices. Each request is processed on the cloud, returning an audio file that matches the input script. This allows for rapid iteration of ad copy without re-recording.
APIs like SpokenWave use standard REST endpoints. Developers send JSON bodies containing the script and voice parameters. The service returns the audio, enabling automated ad production pipelines.
- Input: Up to 4096 characters per request.
- Output: MP3, WAV, OPUS, FLAC, or PCM.
- Format: Compatible with standard ad players.
MP3 format benefits
MP3 files are universally supported by radio automation software and digital ad servers. They offer a balance between audio fidelity and bandwidth efficiency. This ensures that radio spots and digital commercials play correctly on any device.
The format is lightweight, reducing storage and transfer costs. For high-volume ad campaigns, this efficiency scales well without increasing infrastructure overhead.
- Universal compatibility with ad servers.
- Small file size for fast delivery.
- Standard for radio and digital media.
Synthetic audio
Generated audio is synthetic speech created by neural networks. It does not involve human recording but mimics natural speech patterns. Each file contains an inaudible watermark identifying it as synthetic.
This ensures consistency in tone and pacing across all generated spots. The audio is ready for immediate use in advertising campaigns without post-production editing.
- Inaudible watermark in every file.
- No human recording involved.
- Consistent speech patterns.
Technology
SpokenWave converts text into audio files through a cloud API. Requests are sent to the server, processed, and returned as synthetic speech files.
The system handles voice synthesis on the cloud, ensuring consistent output for advertising workflows.
Neural networks
Our engine uses neural network models trained on licensed recordings from LibriTTS-R and LibriVox. These models generate natural-sounding speech from text input.
- Trained on CC BY 4.0 and public domain data
Voice synthesis
The API synthesizes speech using eight distinct voice presets. Each voice is designed for specific advertising tones, from energetic promos to calm narration.
- 8 preset voices available
Cloud processing
Processing occurs on our cloud servers. You send JSON via POST requests, and receive audio files directly in the response.
- REST API endpoint
Advantages
SpokenWave eliminates recurring studio costs by charging $0.01 per 1,000 characters. There are no monthly plans, seats, or minimum spend requirements. You pay only for what you generate, with failed requests free. This model suits startups needing predictable unit economics for advertising campaigns without overhead waste.
Cost efficiency
The API charges $10 per million characters, making long-form radio spots economical. Unlike traditional recording sessions that require fixed time blocks, you generate audio on demand. This allows precise budgeting for high-volume ad production across multiple channels.
- No monthly subscription fees
- Zero charge for failed requests
- Transparent per-character pricing
Scalability
Generate thousands of variations simultaneously without hiring additional voice talent. The cloud infrastructure handles requests sequentially, ensuring consistent throughput. You can scale from one spot to thousands by simply increasing your API key's request volume.
- Instant generation capacity
- No hiring delays for new voices
- Supports bulk ad variations
Consistency
Every generation uses the same licensed voice presets, ensuring brand audio consistency. Unlike human performers who vary in tone or fatigue, SpokenWave delivers uniform quality. Each audio file maintains the same professional standard, critical for multi-channel advertising campaigns.
- Uniform voice tone
- No performance variability
- Standardized output quality
Use in Advertising
SpokenWave enables startups to generate professional audio assets rapidly via a standard REST endpoint. By converting text scripts into MP3 or WAV files, teams can produce voiceovers without booking studio time or coordinating talent schedules.
The API accepts input text up to 4,096 characters per request, allowing for concise spot generation. With speeds ranging from 0.25x to 4.0x, creators can adjust pacing to fit exact ad durations, ensuring precise timing for broadcast and digital placements.
Radio spots
Generate high-quality voiceovers for local and national radio campaigns in seconds. The API supports 23 languages, including English, German, and Spanish, allowing for multi-regional ad rotations without hiring separate voice talent for each market.
- Instant generation of 30-60 second spots
- Consistent brand voice across all regions
- No studio booking or session fees
Digital ads
Integrate TTS directly into ad tech stacks to personalize audio creatives at scale. Each request returns a downloadable audio file, which can be dynamically inserted into HTML5 banners or video ads based on user segments.
- Dynamic voice insertion for programmatic ads
- Support for MP3, WAV, and Opus formats
- Low latency suitable for dynamic insertion
Podcast ads
Produce host-read style ad reads for podcast networks using presets like "Sage" or "Milo." The synthetic audio carries an inaudible watermark, verifying its origin while maintaining a professional tone suitable for mid-roll placements.
- Natural-sounding presets for ad reads
- Automated batch generation for multiple episodes
- Cost-effective alternative to voice talent
Integration
SpokenWave’s API uses a standard REST endpoint compatible with existing OpenAI SDKs. Send a JSON payload with your API key to receive synthesized audio files in formats like MP3 or WAV. The system handles character splitting for longer scripts, ensuring consistent output without manual intervention.
API usage
Integration begins by setting the base URL to https://api.playgo90.com/v1. Use the POST method to send text, selected voice, and language parameters. The response returns the audio file directly, ready for immediate playback or storage in your ad inventory.
- Standard JSON request body
- Bearer token authentication
- Supports MP3, WAV, Opus, FLAC, PCM
Automation
Connect your TTS engine to your campaign management tools via simple HTTP requests. Scripts can generate voiceovers on demand for dynamic ad insertion, allowing real-time personalization of radio spots without human voice actors.
Workflow
Developers can integrate the API into CI/CD pipelines for automated audio asset creation. Generate test variants quickly using different voices like Aria or Felix, then deploy the final audio file to your media server for immediate ad rotation.
Quality
SpokenWave converts text into synthetic audio using licensed voice recordings. The output is clean, clear, and free of background noise, making it ready for immediate use in advertising campaigns without extensive post-production.
We do not claim human-like emotion or inflection. Voices like Aria and Felix provide clear tones appropriate for ads. The synthetic nature is marked by an inaudible watermark, ensuring transparency while maintaining high audio integrity.
Natural sound
Audio files are generated in standard formats like MP3, WAV, or FLAC. The synthesis engine delivers consistent audio quality regardless of text length, up to 4,096 characters per request. This ensures that every ad spot maintains a uniform sonic profile across your campaign.
- Supports MP3, WAV, OPUS, FLAC, and PCM formats
- Consistent audio quality across all generated clips
- Inaudible watermark marks synthetic speech
Human-like
Voices are based on licensed recordings from LibriTTS-R and LibriVox. They offer distinct, preset tones such as warm narration or energetic promo styles. They do not mimic human emotional cues but provide reliable, clear delivery suitable for commercial contexts.
- 8 preset voices with distinct tones
- Based on licensed recordings
- No emotional inflection or mimicry
Professional
Professional Output is suitable for radio spots and digital ads. The API handles speed adjustments from 0.25x to 4.0x, allowing you to fit audio precisely into time-constrained media buys. The output is clean and requires minimal editing before broadcast.
- Adjustable speed (0.25–4.0x)
- Clean audio for direct broadcast
- Minimal post-production required

Limitations
SpokenWave delivers reliable synthetic audio for advertising, yet specific technical constraints define the integration workflow. Understanding these boundaries ensures accurate budgeting and correct API implementation for radio spots and digital campaigns.
Character limits
Each API request accepts a maximum of 4096 characters. Inputs exceeding this limit must be split into smaller chunks and joined sequentially. Spaces and punctuation count toward the total, requiring precise text management before synthesis.
No streaming
The service does not support WebSocket or real-time partial audio streaming. Clients receive the complete audio file only after the entire request is processed. This synchronous model suits batch production but may introduce latency for interactive applications.
No SSML
Standard Speech Synthesis Markup Language (SSML) is not supported. Users cannot inject custom pauses, emphasis, or phoneme changes via markup. Voice control relies entirely on the eight available presets and the speed parameter.
Comparison
SpokenWave provides a standardized API compatible with standard SDKs, simplifying integration for ad tech workflows. It delivers synthetic audio with consistent quality across all requests, ensuring predictable output for high-volume advertising campaigns.
Vs human voice
Human narration requires casting, studio booking, and editing time. SpokenWave generates audio via a REST endpoint, eliminating scheduling delays. Voices like Felix suit energetic promos, while Atlas provides neutral news tones.
Vs other TTS
SpokenWave supports 23 languages and offers eight distinct voice presets, including options for energetic promos and calm narration. It uses licensed recordings from LibriVox, providing clear, synthetic speech without the variability of legacy systems.
Vs recording
Traditional recording incurs fixed studio costs per hour. SpokenWave charges $0.01 per 1,000 characters, making it cost-efficient for short spots. Failed requests are free, reducing financial risk during campaign testing.
Implementation
SpokenWave integrates via a standard REST endpoint compatible with existing SDKs. Start by generating an API key on /get-api-key/ and sending POST requests with your text payload.
Setup steps
Register via Google or email to receive a bearer token. Configure your SDK’s base_url to https://api.playgo90.com/v1 and pass your model, voice, and input text in the JSON body.
- Obtain API key from dashboard
- Set base_url to https://api.playgo90.com/v1
- Pass JSON payload with model and voice
Testing
Use the free $0.50 trial credit to verify audio quality. Check that the generated MP3 or WAV matches your script’s timing and tone requirements before scaling.
Deployment
Implement character splitting logic for texts exceeding 4096 characters. Ensure your automation handles the 60 requests per minute limit to prevent queue delays during peak ad production.
Support
SpokenWave provides comprehensive resources to help startups integrate the TTS API efficiently into their advertising workflows. Our documentation details every endpoint, parameter, and authentication method required for seamless deployment.
Developers can access ready-to-use code snippets and configuration guides that simplify the integration process, ensuring quick implementation of text-to-speech capabilities in ad campaigns.
Documentation
The API reference covers all endpoints, including speech synthesis and voice listing. Detailed explanations of request fields like model, voice, and speed ensure precise control over audio output.
- Complete API reference
- Authentication guide
- Error code list
Examples
Ready-to-use curl commands and SDK configurations are provided. These examples demonstrate standard requests for generating MP3 and WAV files, allowing developers to test immediately.
- cURL examples
- Python SDK config
- Node.js snippets
Contact
Support is available via email for technical inquiries and billing questions. Response times are standard for email support, with no live chat or phone lines.
- Email support only
- No live chat
- No phone support
FAQ
Frequently asked questions address core functionality, such as character limits and supported formats. Users often inquire about authentication methods and billing cycles for advertising campaigns.
Troubleshooting covers common issues like rate limits or failed synthesis. Updates section notes the lack of SSML support and streaming capabilities, clarifying that requests are processed sequentially.
Common questions
How many characters can I send? Each request supports up to 4096 characters. Longer texts must be split and joined by the client.
Do I need an SDK? No. Use standard HTTP requests or the OpenAI SDK with the adjusted base URL.
- Supported formats: mp3, wav, opus, flac, pcm
- Rate limit: 60 requests per minute per key
Troubleshooting
If synthesis fails, the charge is returned in full. Check your API key and ensure the text is under the character limit.
For queuing delays, note that requests are processed one after another under load.
Updates
We do not offer SSML, streaming, or custom voice cloning. Voice presets remain fixed.
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.
