Cloud Text-to-Speech API with 8 Voices and 23 Languages

By SpokenWave editorial team · Updated 2026-11-18

This page explains the technical foundation of SpokenWave, a cloud text-to-speech API designed for startups creating advertising and radio spots. We provide a simple REST endpoint compatible with standard SDKs, offering 8 voice presets and support for 23 languages.

Read on to understand our data policy, voice licensing sources, and technical limitations. This information is essential for developers integrating our service into their production workflows, ensuring transparency regarding input usage, audio storage, and support channels.

Cloud Text-to-Speech API with 8 Voices and 23 Languages

Frequently asked questions

Who runs SpokenWave?

SpokenWave is an independent storefront for a cloud text-to-speech API. We operate as a standalone entity providing REST endpoints compatible with standard SDKs. Our service is designed for developers and startups requiring reliable audio generation without affiliation to larger technology brands or third-party platforms.

Where do the voices come from?

Our eight voice presets are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Each generated audio file carries an inaudible watermark that identifies it as synthetic speech, ensuring transparency regarding the origin and nature of the generated content.

Is SpokenWave affiliated with OpenAI?

No. We are not affiliated with OpenAI, ElevenLabs, Google, Amazon, Microsoft, or any other brand mentioned in comparisons. Our API endpoint structure mirrors the OpenAI speech endpoint for compatibility, but we are an independent provider using our own infrastructure and pricing models.

How is my data used?

Input text is used solely to produce the audio response and is not used for training models. We retain request metadata, including time, character count, and status, strictly for billing purposes. No other personal data or usage patterns are stored beyond what is necessary for service delivery.

Do you store audio files?

Generated audio is returned directly in the API response and is not stored on our servers. Only the request metadata required for billing and usage tracking is retained. This ensures that your specific audio outputs remain transient and are not kept in our long-term storage.

Can I contact you by phone?

No. We do not offer a phone number or live chat support. All customer support is handled exclusively via email. This allows us to maintain a direct line of communication for technical inquiries and billing issues without the overhead of telephony infrastructure.

What is your email address?

Support is available by email only. Please direct your inquiries to the contact address provided on our /contact/ page. We do not have a dedicated phone line, so email remains the single point of contact for all customer service and technical support needs.

Do you have an SLA?

We do not provide a Service Level Agreement (SLA) or uptime guarantee. Our service is offered on an as-available basis without enterprise contracts. While we strive for reliability, there is no formal commitment regarding specific availability percentages or response times for support tickets.

Are you HIPAA compliant?

We do not hold HIPAA compliance certifications. Our service is designed for general commercial use, such as advertising and radio spots, rather than healthcare data handling. We do not offer specific certifications or on-premise installations required for strict regulatory environments like HIPAA.

Do you offer enterprise plans?

No. We offer a simple pay-as-you-go model with no monthly plans, seats, or minimum spend requirements. There are no enterprise contracts or custom pricing tiers. You pay only for the characters you consume, with no long-term commitments or volume-based tiered structures.

How do you handle disputes?

Disputes are handled via email support. Since we do not have phone support, all communications are conducted electronically. We resolve billing and service issues through our email channel, maintaining a record of all interactions for transparency and accountability.

What is your return policy?

Failed requests are free; if synthesis fails, the charge is returned in full. There is no separate return policy for audio files since they are not stored. Your balance does not expire, and you can retain unused credit indefinitely without any expiration date.

Do you have a physical address?

Our infrastructure is distributed, and all business operations, including billing and support, are managed remotely through our digital channels.

Who is the CEO?

Our focus remains on the technical delivery of the TTS API rather than corporate hierarchy or leadership branding.

Who we are

Sound wave illustration for: Who we are

SpokenWave is a cloud text-to-speech API engineered specifically for startups developing advertising and radio spots. We provide a reliable, standardized REST endpoint that integrates with existing development workflows, allowing teams to convert marketing copy into high-quality audio files without managing infrastructure.

Our architecture is built on the OpenAI-compatible request shape, ensuring that standard SDKs work out of the box with minimal configuration. This approach reduces integration time for engineering teams, letting you focus on creative content rather than audio processing logistics.

Startup focus

Startup focus

We understand that marketing campaigns require rapid iteration and scalable audio generation. Our API is designed to handle the bursty traffic patterns typical of product launches, where large volumes of text need to be converted into MP3 or WAV files quickly.

  • Optimized for advertising and radio spot production workflows
  • Simple REST integration compatible with standard SDKs
  • No minimum spend or complex enterprise contracts

Independent team

Independent team

SpokenWave is an independent team operating the playgo90.com storefront. We are not a subsidiary of OpenAI, ElevenLabs, or any major tech platform. Our development decisions are driven by the specific needs of small teams rather than broad platform scaling requirements.

  • Operated independently under the SpokenWave brand
  • Direct access to API key management and billing
  • Support provided via email, ensuring direct communication

Mission

Mission

Our mission is to make high-quality synthetic speech accessible to startups without the overhead of enterprise voice platforms. By providing clear licensing terms and straightforward pricing, we enable teams to produce radio spots and audio ads efficiently and legally.

Voice licensing

Sound wave illustration for: Voice licensing

SpokenWave derives its eight voice presets from licensed recordings of the LibriTTS-R dataset. This dataset consists of audiobook readings sourced from LibriVox, a community-driven project that provides public domain audio content. By utilizing these established recordings, we ensure a consistent and high-quality synthetic voice foundation for our API users.

LibriTTS-R source

LibriTTS-R source

Our voice models are trained on audio data from the LibriTTS-R dataset. These recordings originate from LibriVox, which aggregates readings of books that have entered the public domain. This source provides a diverse range of vocal styles, which we have curated into eight distinct presets for advertising and radio spot generation.

  • Based on LibriTTS-R dataset recordings
  • Originates from LibriVox community readings
  • Curated for consistent voice quality

CC BY 4.0 license

The underlying audio data is available under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This legal framework allows for the use, adaptation, and distribution of the source material, provided appropriate credit is given. Our use of this license ensures that our voice engine rests on a clear and permissive legal basis.

Public domain

The literary works read in the LibriVox recordings are in the public domain. This means the original texts are free from copyright restrictions, allowing for broad usage in commercial contexts such as advertising spots. The combination of public domain texts and CC BY 4.0 licensed audio provides a robust foundation for our TTS service.

Data policy

Sound wave illustration for: Data policy

SpokenWave processes input text solely to generate the requested audio file. The text is not used for training models or improving voice synthesis quality. Generated audio is returned in the response and is not stored on our servers after delivery.

Input text usage

Your input text is processed exclusively for synthesis and is never used to train our models or improve voice quality. This ensures that your specific copy remains private to your application’s workflow.

Audio storage

Generated audio files are returned directly in the API response and are not stored on our servers. Once the response is delivered to your client, the audio data is not retained by SpokenWave.

Billing data

Request metadata, including timestamp, character count, and status, is kept for billing purposes. This data ensures accurate charging based on the $0.01 per 1,000 characters rate and helps resolve any discrepancies in usage.

Contact

Sound wave illustration for: Contact

SpokenWave provides email support for all account and API inquiries. We do not offer a phone number or live chat, maintaining a lean, asynchronous workflow suited for developer teams.

Our contact address is [email protected]. This is the single point of contact for billing, technical issues, and general questions.

Email support

Send all inquiries to [email protected]. This channel handles everything from API key issues to billing questions. We do not maintain separate support queues for different product lines.

No phone number

We do not provide a phone number. All communication is conducted via email to ensure a clear written record of technical details and account changes.

Response time

Response times may vary during peak periods or holidays.

  • Standard business days apply
  • Weekend responses may be delayed
Contact

Technical limits

Sound wave illustration for: Technical limits

The SpokenWave API is designed for batch processing and standard REST workflows, not for live audio delivery. Requests are processed sequentially, meaning under load a request may wait in a queue before synthesis begins. This architecture ensures stability but does not support real-time partial audio streaming via WebSocket or HTTP chunking.

Unlike enterprise-grade TTS engines, SpokenWave does not interpret SSML markup. You cannot adjust prosody, pause durations, or pronunciation within the API call itself. Additionally, the service offers eight fixed voice presets and does not support custom voice cloning. All generated files carry an inaudible watermark indicating synthetic origin.

No streaming

The API returns complete audio files upon request completion. There is no support for WebSocket connections or HTTP streaming endpoints that deliver audio chunks in real-time. For applications requiring immediate audio playback during generation, you must implement client-side buffering or use the full file response after the request finishes. Typical generation speed is roughly real-time on long texts; short phrases take a few seconds.

  • Full file response only; no partial audio chunks
  • Sequential processing may cause queue delays under load
  • Suitable for batch jobs and pre-generated audio assets

No SSML

SpokenWave does not parse SSML tags. You cannot use tags to control pronunciation, add pauses, or adjust emphasis within the input text. The voice engine relies on natural language processing to determine pacing and intonation based on the provided text alone. If precise control over timing or pronunciation is required, it must be handled at the application layer before sending the text to the API.

  • Plain text input only
  • No <break>, <prosody>, or <phoneme> support
  • Pacing determined by the TTS engine’s natural language processing

No custom cloning

The service provides eight predefined voice presets and does not offer custom voice cloning features. You cannot upload a reference audio file to create a unique voice model based on your own recordings or a specific person’s voice. Each generated file includes an inaudible watermark that marks it as synthetic speech, distinguishing it from human-recorded audio. This ensures transparency regarding the origin of the audio content.

  • Fixed set of 8 voice presets
  • No upload of reference audio for cloning
  • Inaudible watermark in all generated files

Affiliations

Sound wave illustration for: Affiliations

SpokenWave operates as an independent entity, providing a cloud text-to-speech API that is distinct from major technology providers. Our infrastructure and voice models are managed separately, ensuring our service remains focused on the specific needs of startups creating advertising and radio spots.

Not OpenAI

Although our API endpoint and request body structure mimic the OpenAI speech endpoint for ease of integration, we are not affiliated with OpenAI. We do not use OpenAI’s models, and our pricing, voice presets, and data policies are entirely separate. Developers using the OpenAI SDK with a custom base_url are using our independent service.

Independent

SpokenWave is built and maintained by an independent team. We do not rely on third-party TTS engines for our core synthesis. Our 8 voice presets and 23 language support are processed through our cloud infrastructure.

No partnerships

We currently have no formal partnerships with other TTS providers, voice agencies, or platform integrations. Our focus remains solely on delivering a reliable, straightforward API for developers. Any future collaborations will be announced explicitly on our contact and docs pages.

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. FFmpeg documentation
  3. MDN: Web Speech API
  4. curl documentation
  5. openai-node on GitHub
  6. openai-python on GitHub
  7. IETF RFC 7845: Ogg Opus
  8. TRON developer hub: TRC-20
  9. Python documentation
  10. LibriVox public-domain audiobooks
  11. Creative Commons Attribution 4.0
  12. LibriTTS-R corpus (OpenSLR 141)

More on this site