Frequently asked questions
What is a text to audio reader API?
It is a cloud API that accepts text input and returns an audio file. You send a POST request to the speech endpoint with your text and voice selection. The service processes the request and returns the generated audio asset, allowing newsroom teams to programmatically convert articles into listenable content for distribution.
How does text to audio conversion work for news articles?
Send text via a POST request to the speech endpoint. The system synthesizes the audio using selected voices and returns the file. For texts exceeding 4096 characters, split the input into parts and join the resulting audio files. Typical generation speed is roughly real-time, producing about 25 characters of text per second of audio.
Which voices are available for news content?
Eight presets are available. For news, use atlas (neutral, news) or milo (friendly, conversational). Other options include aria, nova, luna, sage, felix, and orion. All voices are based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech.
What languages are supported by the API?
The API supports 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. If the language is not specified, it is guessed from the script.
How is pricing calculated for audio generation?
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 the charge returned in full. There are no monthly plans, seats, or minimum spends. Balance does not expire, and top-ups are processed via USDT on the TRON network.
Is the API compatible with OpenAI SDKs?
Yes. The endpoint shape matches the OpenAI speech endpoint. You can use the official OpenAI SDKs by changing the base_url to https://api.playmomoo.com/v1 and using your site-specific key. The request fields include model, input, voice, response_format, and speed, ensuring compatibility with standard integration workflows.
Can I use the API for breaking news notifications?
Yes, the API supports generation for notifications. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time. For breaking news, ensure your integration handles the response format and manages the queue if multiple requests are sent simultaneously.
Are input texts used for training models?
No. Input text is used only to produce the audio and is not used for training. Generated audio is returned in the response and not stored. Only request metadata, such as time, characters, and status, is kept for billing purposes. Your content remains private during the generation process.
What happens if an audio generation request fails?
If synthesis fails, the charge is returned in full. You are not billed for unsuccessful requests. This ensures that network issues or processing errors do not incur costs. You can retry the request with the same text and parameters without financial penalty.
How many characters can be processed per request?
Each request supports up to 4096 characters in the input field. For longer articles, split the text into parts of this size and join the resulting audio files. This limit ensures efficient processing and allows for precise control over audio segmentation during integration.
Does the API support long-form article conversion?
Yes. Split long texts into parts of up to 4096 characters and join the audio files. Typical speed is roughly real-time, generating about 25 characters per second. Requests are processed sequentially, so under load, a request may wait in a queue before synthesis begins.
What audio formats are supported?
The API supports mp3, wav, opus, flac, and pcm formats. Specify the desired format in the response_format field of your POST request. This allows newsrooms to choose the optimal format for their distribution channels, whether for web streaming, archival, or mobile applications.
How do I top up my account balance?
Top up using USDT on the TRON network (TRC-20) only. The minimum top-up is $5. Credits are added automatically within minutes after the transfer. There are no cards, PayPal, or subscriptions. Balance does not expire. You can issue a new API key at any time via the dashboard.
Is there a free trial available for newsrooms?
Yes, a free trial provides $0.50 of credit, valid for 7 days. This allows approximately 50,000 characters of generation. The trial is available when signing in with Google. Accounts created with email and password start without trial credit. No credit card is required to start.
First request
curl
curl https://api.playmomoo.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.mp3Automated Audio Generation for Newsrooms
NewsAudio Reader provides an API-driven text-to-speech integration designed for newsroom product teams. By sending text via a standard REST endpoint, teams can convert articles and transcripts into audio assets programmatically. The system accepts JSON bodies and returns immediate audio files, enabling seamless embedding into content management systems without manual intervention.
API-driven text-to-speech integration
The endpoint POST https://api.playmomoo.com/v1/audio/speech accepts up to 4,096 characters per request. Developers can use official OpenAI SDKs by adjusting the base URL, ensuring compatibility with existing infrastructure. This approach allows for automated generation of audio versions for long-form journalism or breaking news updates.
- Standard JSON request body
- Immediate audio file delivery
- Compatible with OpenAI SDKs
Accessibility compliance for articles
Generating audio assets supports accessibility standards for readers who prefer or require auditory content. The API processes text efficiently, with typical speeds nearing real-time for long texts. Each generated file includes an inaudible watermark to identify synthetic speech, maintaining transparency for compliance audits.
Multi-language content expansion
The API supports 23 languages, allowing newsrooms to localize content across different regions without hiring multiple voice actors. Any voice preset can speak any supported language, ensuring consistent branding. This enables rapid expansion into markets such as Spanish, German, or Japanese with uniform audio quality.
Supported Languages and Voices
The API supports 23 languages, including English, Spanish, German, French, Japanese, and Arabic. Any voice preset can render any supported language, allowing newsrooms to localize content without managing separate voice models. If the language is not specified, the system guesses from the script, defaulting to English for Latin text.
23 languages with native synthesis
Supported languages are Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Texts in other scripts or languages not listed, such as Vietnamese or Thai, are not supported.
Neutral and conversational voice presets
Eight voice presets are available, based on licensed recordings from LibriTTS-R and LibriVox. Options range from the warm narrator Aria to the deep documentary tone of Orion. All generated audio files include an inaudible watermark to mark them as synthetic speech.
- 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
Consistent branding across regions
Using the same voice presets across different language versions ensures a consistent auditory brand identity for international news desks. Teams can maintain uniform tone and pacing regardless of the target market's language.

Technical Specifications
The API endpoint follows the standard OpenAI speech request shape, allowing newsroom engineering teams to reuse existing OpenAI SDKs by simply updating the base URL to https://api.playmomoo.com/v1. Authentication is handled via a single active Bearer token, which can be rotated instantly if needed.
OpenAI SDK compatibility
Developers can integrate using official OpenAI libraries with minimal configuration changes. The request structure mirrors the standard speech endpoint, ensuring familiarity for teams already accustomed to modern TTS integrations.
- Base URL: https://api.playmomoo.com/v1
- Auth: Authorization: Bearer <key>
- Compatible with official OpenAI SDKs
Standard audio formats (MP3, WAV, FLAC)
Audio output is delivered in MP3, WAV, OPUS, FLAC, or PCM formats. This flexibility allows news platforms to optimize for archival storage or ingestion pipelines without additional conversion steps.
Instant audio file delivery
Requests are processed sequentially, typically completing in real time for long texts. Short phrases take a few seconds, while longer articles generate audio at a rate of approximately 25 characters per second. Failed requests incur no charge and return immediately.
Pricing Structure
The API charges $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. This per-character model ensures predictable costs for high-volume newsroom deployments, from short alerts to lengthy articles.
Per-character billing model
Billing is calculated directly on input length. Requests are processed individually, and failed synthesis returns the full charge, ensuring you only pay for successful audio generation.
Volume-based cost efficiency
Costs scale linearly with usage. There are no monthly plans, seats, or minimum spend requirements. Balance does not expire, allowing flexible budgeting for irregular news cycles.
Transparent usage tracking
Account dashboards display current balance, characters remaining, and usage history. Request metadata, including time and status, is retained for accurate billing verification without storing generated audio.
- $10 per 1 million characters
- Failed requests are free: if synthesis fails, the charge is returned in full.
Integration Workflow
Integrate NewsAudio Reader into your content pipeline via a standard REST endpoint. The API follows the same request shape as the OpenAI speech endpoint, allowing you to use existing OpenAI SDKs by simply adjusting the base URL to https://api.playmomoo.com/v1. This ensures compatibility with your current development stack without requiring a custom library.
Authentication is handled via a Bearer token sent in the Authorization header. Each account maintains one active key, which can be rotated instantly if needed. This setup supports both rapid prototyping and production-grade automation for newsroom workflows.
Simple REST endpoint setup
Configure your client to send POST requests to https://api.playmomoo.com/v1/audio/speech. The endpoint accepts JSON payloads and returns audio files directly. You can switch from the OpenAI base URL to our domain by updating the configuration in your SDK or HTTP client.
JSON body request format
Send your article text or transcript in the input field of the JSON body. Specify the model (tts-1 or tts-1-hd), voice preset, and response_format (mp3, wav, opus, flac, or pcm). Optional parameters include speed (0.25–4.0) and language ISO code for precise control over synthesis.
Immediate audio response delivery
The API returns the generated audio file in the response body. For texts exceeding 4096 characters, split the input into segments, generate each part, and join the resulting audio files client-side. Failed requests are free, ensuring no unexpected charges during integration testing.

Quality and Reliability
NewsAudio Reader ensures high-fidelity output by leveraging licensed voice recordings from the LibriTTS-R dataset (CC BY 4.0) and public-domain LibriVox audiobooks. This foundation provides synthesized speech with professional clarity.
Every generated audio file includes an inaudible watermark identifying it as synthetic speech, providing transparency for distribution channels and compliance audits without affecting the listening experience.
Licensed voice recordings
Our eight voice presets are derived from licensed recordings, ensuring legal clarity for commercial newsrooms. The voices range from warm narrators to deep documentary tones, all optimized for clear articulation of journalistic text.
Synthetic speech watermarking
Each audio file carries a subtle, inaudible watermark that marks the content as AI-generated. This feature aids in content tracking and meets emerging disclosure requirements for synthetic media in newsrooms.
Consistent output quality
Requests are processed sequentially, ensuring stable performance even during high-volume usage. While short phrases may take a few seconds, long texts generate at roughly real-time speed, maintaining consistent audio quality across all 23 supported languages.
Use Cases for News Teams
News teams leverage the API to convert written stories into audio assets, ensuring accessibility compliance across digital platforms. By utilizing the tts-1 or tts-1-hd models, editors generate consistent narration for articles up to 4096 characters per request, supporting 23 languages for global expansion.
Audio versions of long-form articles
Split texts exceeding 4096 characters into manageable segments and join the resulting audio files seamlessly. This workflow supports standard formats like MP3 and WAV, allowing product teams to distribute audio articles via web players or mobile apps without manual recording.
- Supports up to 4096 characters per request
- Formats include MP3, WAV, OPUS, FLAC, PCM
- Scales across 23 supported languages
Breaking news voice notifications
Deliver urgent updates via automated voice notifications using presets like atlas for neutral news or felix for energetic promos. The API processes requests sequentially, providing near real-time audio generation suitable for time-sensitive distribution channels.
- Near real-time generation for urgent content
- Dedicated voice presets for tone control
- Instant API response delivery
Podcast-style content automation
Automate the production of podcast-style segments from transcripts or scripts. With eight distinct voice presets and a speed range of 0.25–4.0, teams can maintain consistent branding across regions while generating audio assets efficiently.
- Eight distinct voice presets
- Adjustable speed from 0.25x to 4.0x
- Consistent synthetic voice branding
Data Privacy and Usage
Input text is processed exclusively to generate the requested audio file and is not retained for model training. The generated audio is delivered in the response and not stored on our servers after delivery. This ensures that your article content remains confidential during the synthesis process.
Text used only for synthesis
Your input text is utilized solely for the purpose of generating the audio response. Once the audio file is returned, the text is not archived for other uses.
No training on input data
The text you submit for synthesis is not used to improve or train the underlying TTS engine. Your proprietary content remains distinct from the training dataset.
Metadata retained for billing
We retain request metadata, including timestamp, character count, and status, exclusively for billing and usage tracking purposes. This data supports accurate invoicing and account management.

Getting Started
Create an account on the /get-api-key/ page using Google or an email and password. Accounts are specific to this site and require no monthly subscriptions or minimum spend.
Once registered, retrieve your API key immediately. You can issue a new key at any time, which invalidates the old one instantly. Use the key with the Authorization header for all requests.
Create an account via Google or email
Sign up at /get-api-key/ using Google or email/password. Accounts are per site. A $0.50 free trial credit is available for Google sign-ins, valid for 7 days.
- Google or email/password authentication
- Instant account creation
- Free trial credit for Google users
Retrieve API key instantly
Access your active API key and balance directly on the dashboard. One key is active per account; issuing a new one stops the old one immediately.
- Single active key per account
- Instant key invalidation
- Real-time balance tracking
Test with the provided curl example
Use the ready curl example on the dashboard to make your first request. Send a POST to the speech endpoint with your text and voice selection to receive an audio file.
- REST endpoint: POST /v1/audio/speech
- JSON body format
- Standard OpenAI SDK compatibility
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. News outlets will amplify your launch, turning product updates into public conversation for your entire audience.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- MDN: Web Speech API
- OpenAI API reference: create speech
- Node.js documentation
- Python documentation
- W3C WAI: making audio and video accessible
- TRON developer hub: TRC-20
- FFmpeg documentation
- openai-python on GitHub
- LibriTTS-R paper (arXiv 2305.18802)
- openai-node on GitHub
- LibriTTS-R corpus (OpenSLR 141)
