SpokenWave TTS API: Simple Pricing for Ads, Radio & Podcasts

By SpokenWave editorial team · Updated 2026-11-18

This guide explains how startups can use the SpokenWave API to generate advertising and radio spots efficiently. You will find specific details on the eight voice presets, the 23 supported languages, and the straightforward pricing structure of $0.01 per 1,000 characters.

The page covers technical integration steps, including OpenAI SDK compatibility and rate limits, alongside practical use cases for radio and podcast production. It also outlines the USDT payment model, data privacy terms, and support channels to help you deploy synthetic speech into your workflow.

SpokenWave TTS API: Simple Pricing for Ads, Radio & Podcasts

Frequently asked questions

Is SpokenWave good for radio spots?

SpokenWave converts text into audio files via a simple REST endpoint, ideal for generating advertising and radio spots. You can use eight preset voices and multiple formats like MP3 or WAV. The API is compatible with standard SDKs, allowing you to integrate speech generation directly into your production workflow without complex infrastructure.

How does SpokenWave compare to others?

SpokenWave is not affiliated with OpenAI, ElevenLabs, or other brands. It uses a cloud TTS API with a request shape similar to OpenAI’s speech endpoint. Unlike many competitors, it requires no monthly plans or subscriptions. Pricing is strictly usage-based at $0.01 per 1,000 characters, with no minimum spend or seats.

What is the best voice for ads?

The voice choice depends on your specific campaign needs. For energetic promotional spots, Felix is suitable. For a friendly, conversational tone, choose Milo. If you prefer a warm, clear narrator style, Aria is available. All eight voices are licensed recordings and can speak any of the supported 23 languages.

Is SpokenWave cheap?

SpokenWave charges $0.01 per 1,000 characters, including spaces and punctuation. Failed requests are free. There are no monthly plans, seats, or minimum spend requirements. You only pay for the characters you consume, making it cost-effective for startups with variable advertising volumes. Balances do not expire.

Can I use SpokenWave for podcasts?

Yes, SpokenWave supports text-to-speech conversion for various audio needs, including podcast segments. You can generate audio in formats like MP3, WAV, OPUS, FLAC, or PCM. The API handles up to 4,096 characters per request, allowing you to split longer scripts into manageable parts for synthesis.

Does SpokenWave support multiple languages?

SpokenWave supports 23 languages, including English, Spanish, German, French, Japanese, and Arabic. Any voice can speak any supported language. If the language is not specified, it is guessed from the script, but you should set it explicitly for non-English Latin-script text to ensure accuracy.

Is SpokenWave easy to integrate?

Integration is straightforward using standard HTTP requests or the OpenAI SDK. You send a POST request to the speech endpoint with your text, voice, and format. Authentication is handled via a Bearer token. The API is compatible with existing SDKs by simply changing the base URL to the SpokenWave domain.

What audio formats does SpokenWave support?

SpokenWave supports MP3, WAV, OPUS, FLAC, and PCM formats. You can specify the desired format in the request body. This flexibility allows you to choose the appropriate file type for your advertising or radio spot production pipeline, whether for web playback or broadcast delivery.

Does SpokenWave have a free trial?

Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This allows approximately 50,000 characters of generation. Accounts created with email and password start without trial credit. You can top up your balance using USDT on the TRON network to continue generating audio.

Is SpokenWave suitable for startups?

SpokenWave is designed for startups needing scalable speech generation. There are no monthly plans, seats, or minimum spend requirements. You pay only for what you use at $0.01 per 1,000 characters. The simple REST API integrates easily into existing workflows without requiring enterprise-level contracts or complex infrastructure.

How fast is SpokenWave?

Generation speed is roughly real-time, processing about 25 characters per second for long texts. Short phrases may take a few seconds. Requests are processed sequentially, so under heavy load, a request may wait in a queue. The API returns the audio file once synthesis is complete.

Can I use SpokenWave for IVR?

SpokenWave can generate audio for IVR systems by converting text to speech files. You can specify voices like Atlas for a neutral, news-like tone or Milo for a conversational style. The API supports multiple languages and formats, allowing you to create consistent audio assets for your phone system.

Does SpokenWave offer customer support?

Support is available via email only. There is no phone number, live chat, or SLA guarantee. You can reach out for assistance with integration or billing issues. The product does not offer enterprise contracts or dedicated support channels.

How do I top up my balance?

You can top up your balance using USDT on the TRON network (TRC-20). The minimum top-up amount is $5. Credits are added automatically within minutes after the transfer is confirmed. There are no subscriptions or invoices with VAT. Your balance does not expire once credited.

Why SpokenWave for Advertising?

Sound wave illustration for: Why SpokenWave for Advertising?

SpokenWave delivers consistent audio quality for advertising campaigns at a predictable rate of $0.01 per 1,000 characters. This transparent pricing model eliminates hidden fees, allowing startups to forecast production costs accurately without negotiating enterprise contracts or managing complex subscription tiers.

Transparent pricing

Each request is charged based on character count, including spaces. Failed requests incur no cost, ensuring you pay only for usable audio. This structure supports high-volume generation for radio spots without upfront commitments.

High-quality voices

The API provides eight distinct voice presets, ranging from warm narrators to energetic promo speakers. These voices, derived from licensed recordings, produce clear synthetic speech suitable for professional advertising contexts. An inaudible watermark identifies generated files as synthetic.

Easy integration

Integration requires only a standard HTTP POST request to the /v1/audio/speech endpoint. The request shape mirrors the OpenAI speech endpoint, allowing immediate use of existing OpenAI SDKs by simply adjusting the base URL. This compatibility reduces development time for engineering teams.

SpokenWave Overview

Sound wave illustration for: SpokenWave Overview

SpokenWave delivers a robust text-to-speech API tailored for advertising and radio spot production. The system converts input text into high-quality audio files, supporting eight distinct voice presets and twenty-three languages to ensure precise tone matching for commercial content.

8 Voice Presets

The API offers eight curated voice options, including female presets like Aria and Nova, and male voices such as Felix and Atlas. These voices are derived from licensed recordings, providing clear, distinct tones suitable for various media formats without requiring custom cloning.

  • Female: Aria, Nova, Luna, Sage
  • Male: Felix, Milo, Atlas, Orion

23 Languages Supported

SpokenWave supports 23 languages, including English, German, Spanish, and Japanese. Any voice can speak any supported language, allowing for consistent audio quality across multilingual campaigns. The system guesses the language from the script if not explicitly set.

  • Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish

OpenAI-Compatible API

The endpoint follows the standard OpenAI request shape, enabling immediate integration using official OpenAI SDKs. Developers simply adjust the base URL to the SpokenWave API domain and use their unique key, ensuring a smooth transition for existing workflows.

Voice Options

Sound wave illustration for: Voice Options

SpokenWave offers eight distinct voice presets, each designed for specific advertising and radio applications. These voices are derived from licensed recordings, ensuring commercial clarity and consistency for your productions.

The selection includes four female and four male voices, covering a range from energetic promo to calm instructional tones. This variety allows advertisers to match the exact mood of their spot without requiring custom voice design.

Female Voices: Aria, Nova, Luna, Sage

Aria provides a warm, clear narrator style suitable for professional voiceovers. Nova offers a bright, upbeat tone ideal for upbeat commercial spots. Luna delivers a soft, storytelling quality, while Sage ensures a calm, instructional presence for explanatory content.

  • Aria: Warm, clear narrator
  • Nova: Bright, upbeat
  • Luna: Soft, storytelling
  • Sage: Calm, instructional

Male Voices: Felix, Milo, Atlas, Orion

Felix is energetic and optimized for promotional content. Milo provides a friendly, conversational tone for relatable ads. Atlas offers a neutral, news-style delivery, and Orion delivers a deep, documentary feel for serious or authoritative spots.

  • Felix: Energetic, promo
  • Milo: Friendly, conversational
  • Atlas: Neutral, news
  • Orion: Deep, documentary

Tone Variety for Different Media

Each voice can speak all 23 supported languages, allowing for consistent branding across global campaigns. The licensed source recordings ensure high fidelity, while the inaudible watermark confirms synthetic origin for compliance. These presets cover the spectrum from casual to formal without needing custom cloning.

Pricing & Costs

Sound wave illustration for: Pricing & Costs

SpokenWave charges $0.01 per 1,000 characters for text-to-speech synthesis, with spaces and punctuation counted as characters. Failed requests incur no charge, ensuring you pay only for successful audio generation. This flat rate applies uniformly across all models and voices.

Unlike traditional services, there are no monthly subscriptions, seats, or minimum spend requirements. You top up your balance when needed, and unused credits never expire. This model suits startups with variable advertising volumes, allowing precise cost control per campaign.

$0.01 per 1,000 characters

The cost is calculated based on the character count of your input text, including spaces and punctuation. At this rate, generating one hour of speech typically costs approximately $9.00, scaling predictably for longer radio spots.

No monthly subscriptions

There are no recurring fees, annual contracts, or per-seat licenses. You pay strictly for what you use, making it easy to integrate TTS costs directly into your production budget without worrying about unused capacity.

Free trial credit included

Signing in with Google provides $0.50 in trial credit, valid for 7 days, allowing you to test approximately 50,000 characters. Email-based accounts start with zero balance, requiring immediate top-up via USDT to begin generation.

Technical Features

Sound wave illustration for: Technical Features

The SpokenWave API uses a standard REST endpoint compatible with existing SDKs. Send a POST request to /v1/audio/speech with your text and voice selection to receive an audio file. The service handles the conversion, allowing developers to integrate TTS into their advertising workflows with minimal code changes.

Requests are processed sequentially, so under load a request may wait in a queue. Typical generation speed is roughly real time, producing about 25 characters of text per second. Short phrases take a few seconds to generate, while longer texts are split into parts and joined automatically.

Standard API Endpoint

Interact with the API via POST https://api.playgo90.com/v1/audio/speech. The request body is JSON, containing the model, input text, voice, and response_format. You can use the official OpenAI SDKs by changing the base_url to https://api.playgo90.com/v1 and providing your API key.

Texts are limited to 4096 characters per request. For longer scripts, split the input into chunks of up to 4096 characters, generate each part, and join the resulting audio files. The language field is optional; if omitted, the system guesses the language from the script, defaulting to English for Latin text.

  • Endpoint: POST /v1/audio/speech
  • Auth: Bearer token in Authorization header
  • Max input: 4096 characters per request

Rate Limits: 60 req/min

Each API key is limited to 60 requests per minute. Before the first top-up, the limit is 10 requests per minute. This limit applies per key, so a single account can manage multiple keys if higher throughput is required, though each key has its own limit.

Requests are processed one after another, meaning under load a request may wait in a queue. Plan your batch processing accordingly to avoid delays. Failed requests do not count against your character balance and are free, ensuring you only pay for successful synthesis.

  • Standard limit: 60 requests per minute
  • Pre-top-up limit: 10 requests per minute
  • Processed sequentially; queueing possible under load

Multiple Audio Formats (MP3, WAV, etc.)

Select your preferred audio format using the response_format field. Supported formats include mp3, wav, opus, flac, and pcm. Choose mp3 for smaller file sizes suitable for web delivery, or wav/flac for high-quality archival needs. Each generated file carries an inaudible watermark marking it as synthetic speech.

The audio is returned directly in the response, allowing immediate playback or storage. No additional processing is required to extract the audio data, though the audio is returned directly in the response and not stored. Ensure your integration handles the binary response correctly based on the format you selected in your request.

  • Supported formats: mp3, wav, opus, flac, pcm
  • Inaudible watermark applied to all outputs
  • Immediate response with no storage required

Use Cases

Sound wave illustration for: Use Cases

SpokenWave provides a reliable text-to-speech API tailored for startups creating advertising and radio spots. By converting text into MP3, WAV, and other audio formats via a simple REST endpoint, teams can generate high-quality voiceovers without hiring voice talent or renting studios.

Radio Spots

Generate concise, energetic voiceovers for promotional campaigns using presets like Felix or Milo. The API supports up to 4096 characters per request, allowing for standard 30-second spot scripts in a single call, though generation speed is roughly real time. With formats like MP3 and WAV, files are immediately compatible with broadcast automation systems.

  • Fast generation for time-sensitive ad campaigns
  • Compatible with standard broadcast audio formats
  • Consistent voice quality across multiple spots

Podcast Production

Produce consistent intro/outro segments or fill narration for long-form content. Voices like Luna or Sage offer a storytelling tone suitable for narrative-driven podcasts. Use the language parameter to ensure accurate pronunciation for non-native listeners, and split longer scripts into 4096-character parts to maintain audio quality.

  • Consistent branding across episodes
  • Easy script splitting for long texts
  • Support for 23 languages for global reach

IVR Systems

Create clear, instructional voice prompts for automated phone systems. Atlas provides a neutral, professional tone ideal for menu navigation. With a speed range of 0.25–4.0, you can adjust delivery for clarity. Each request returns an audio file directly, eliminating the need for external hosting or complex pipelines.

  • Clear, professional tone for customer service
  • Adjustable speed for optimal comprehension
  • Simple integration via standard REST endpoint

Integration Ease

Sound wave illustration for: Integration Ease

The SpokenWave API mirrors the OpenAI speech endpoint structure, allowing your existing integration logic to work with minimal code changes. By updating the base_url to https://api.playgo90.com/v1, you can utilize standard OpenAI SDKs for Python, Node.js, or other supported languages without rewriting core request handlers.

OpenAI SDK Compatible

Use the official OpenAI SDKs by simply changing the base_url to https://api.playgo90.com/v1. Pass your tts-... API key via the Authorization: Bearer header. This ensures your application remains compatible with standard development patterns used across the industry.

  • Use standard OpenAI SDKs with a base_url change
  • Compatible with Python, Node.js, and other major languages
  • Standard Authorization: Bearer header authentication

Simple cURL Examples

Start immediately with a ready-to-use cURL command provided on the /get-api-key/ page. Send a POST request to /v1/audio/speech with your JSON body containing model, input, voice, and response_format. This allows for rapid testing and verification of audio output before full integration.

  • Direct POST to /v1/audio/speech
  • JSON body with model, input, voice, response_format
  • Immediate verification of audio generation

Clear Documentation

The /docs/ page details all request fields, including optional parameters like speed and language. It specifies the exact character limits, supported voice presets, and available audio formats. This clarity reduces development time by eliminating guesswork during the integration phase.

Integration Ease

Support & Licensing

Sound wave illustration for: Support & Licensing

Support for SpokenWave is handled exclusively via email. We do not maintain a phone line or offer live chat, ensuring that all inquiries are documented and addressed systematically without wait times associated with voice support channels.

Email Support Only

Our support team manages all technical and billing questions through email. This approach allows for detailed review of your specific use case, whether it involves integration issues or pricing clarifications. There is no phone number to call; all communication is asynchronous.

Commercial Use Allowed

Audio generated via the SpokenWave API is cleared for commercial use. Startups and advertising agencies can use the output in radio spots, podcasts, and IVR systems without additional licensing fees. The synthetic nature of the voice allows for broad commercial application.

Licensed Voice Recordings

The eight voice presets are based on licensed recordings from the LibriTTS-R dataset under CC BY 4.0. These voices originate from LibriVox public-domain audiobook readings. The voices are based on licensed recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain audiobook readings from LibriVox.

Getting Started

Sound wave illustration for: Getting Started

Create an account on the /get-api-key/ page using your Google credentials or a standard email and password. Your account is tied to this specific site and provides immediate access to the dashboard.

Upon sign-in, you receive a unique API key. If you signed in with Google, you also receive a $0.50 free trial credit valid for seven days to test the service.

Get Your API Key

The dashboard displays your active API key, current balance, and character usage statistics. You can regenerate this key at any time; the previous key becomes invalid immediately.

Note that accounts created with email and password start without trial credit. The key is used in the Authorization header as Bearer tts-....

  • Keys are generated per site
  • Regeneration invalidates old keys instantly
  • View balance and usage in real-time

Make Your First Request

Send a POST request to https://api.playgo90.com/v1/audio/speech with your text and selected voice. The API returns an audio file in your chosen format, such as MP3 or WAV.

Ensure your input text does not exceed 4096 characters. For longer scripts, split the text and join the resulting audio files.

  • Endpoint: POST /v1/audio/speech
  • Auth: Bearer <your-key>
  • Max input: 4096 characters

Conclusion

Sound wave illustration for: Conclusion

SpokenWave delivers a reliable, transparent text-to-speech API tailored for startups producing advertising and radio spots. With eight distinct voice presets, support for 23 languages, and simple pricing at $0.01 per 1,000 characters, the service eliminates complex subscriptions while maintaining high audio quality.

The API is fully compatible with standard OpenAI SDKs, allowing for straightforward integration into existing workflows. By using licensed recordings and offering clear commercial usage rights, SpokenWave ensures that generated audio is ready for broadcast without additional licensing hurdles.

Summary of Benefits

The platform combines cost efficiency with technical simplicity. You pay only for what you use, with no monthly commitments or hidden fees. The inclusion of a free trial credit allows for immediate testing of voice quality and API performance before committing to larger volumes.

  • Transparent per-character pricing
  • OpenAI SDK compatibility
  • Commercial usage rights included
  • No monthly subscriptions

Who Should Use SpokenWave

This API is designed for startups and small teams that need scalable audio generation for marketing materials. It is ideal for teams producing radio spots, podcast intros, or IVR systems who require consistent voice quality without managing complex infrastructure or hiring voice actors for every project.

Next Steps

Begin by signing up for an account using Google or email to receive your API key. Test the integration using the provided cURL examples or the OpenAI SDK. Once satisfied with the voice output, top up your balance with USDT to start generating audio for your campaigns.

  • Sign up at /get-api-key/
  • Generate your API key
  • Test with cURL or SDK
  • Top up with USDT

Payment & Top-Up

Sound wave illustration for: Payment & Top-Up

SpokenWave utilizes a straightforward payment model designed for startups. All top-ups are processed exclusively via USDT on the TRON network (TRC-20). This single-currency approach eliminates currency conversion fees and simplifies accounting for international advertising teams.

Users must deposit a minimum of $5.00 to top up their balance. The system automatically credits the wallet within minutes of confirming the blockchain transaction, ensuring no downtime between funding and content generation.

USDT (TRC-20) Only

Payments are accepted solely in USDT on the TRON (TRC-20) network. This method avoids traditional banking delays and reduces transaction costs for global clients. Other cryptocurrencies or network standards are not supported.

  • Supported network: TRON (TRC-20)
  • Currency: USDT (Tether)
  • Minimum top-up: $5.00

No Cards or PayPal

We do not process credit cards, debit cards, or PayPal transactions. There are no monthly subscriptions, seats, or minimum spend requirements. This model allows you to pay strictly for what you use, maintaining strict control over advertising budgets.

Instant Balance Credit

Once the blockchain transaction is confirmed, your balance is updated automatically. Credits appear in your account within minutes, allowing immediate start of voice synthesis projects without manual verification delays.

Data & Privacy

Sound wave illustration for: Data & Privacy

SpokenWave processes input text exclusively to generate the requested audio file. This text is not retained for model training or used to improve our underlying voice synthesis engine after the request completes.

Generated audio files are returned directly in the API response and are not stored on our servers. Once the client receives the audio, it is not kept in our infrastructure, ensuring minimal data persistence.

No Training on Input

Input text is used solely for synthesis and is not added to training datasets. Your campaign scripts remain yours, ensuring that proprietary ad copy or internal communications are not repurposed for voice model improvements.

No Audio Storage

Synthesized audio files are transient. We do not store the generated MP3 or WAV files after delivery, reducing storage liabilities and keeping your creative assets under your control from the moment of generation.

Billing Metadata Kept

We retain request metadata, including timestamp, character count, and status, strictly for billing purposes. This ensures accurate invoicing for your TRC-20 top-ups and allows you to verify usage against your API key consumption.

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.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. IETF RFC 7845: Ogg Opus
  3. Creative Commons Attribution 4.0
  4. ISO 639 language codes
  5. TRON developer hub: TRC-20
  6. FFmpeg documentation
  7. W3C WAI: making audio and video accessible
  8. Node.js documentation
  9. LibriTTS-R corpus (OpenSLR 141)
  10. Python documentation
  11. MDN: Web Speech API
  12. Tether (USDT)

More on this site