Frequently asked questions
What is the text to speech AI free tier?
Accounts created with Google receive a $0.50 free trial credit valid for 7 days. Email-based accounts start without trial credit. The service charges $0.01 per 1,000 characters. Failed requests are free, with charges returned in full. There are no monthly plans or subscriptions.
How many characters are included in the free trial?
The free trial provides $0.50 of credit, which equals approximately 50,000 characters. This credit is available only when signing in with Google. Email-based accounts do not receive this trial credit. The credit is valid for 7 days from account creation.
Is the free text to speech AI suitable for commercial audiobooks?
Yes. Generated audio files are returned in the response and not stored. Input text is used only for synthesis and not for training. The API supports 23 languages and 8 voice presets. There are no usage restrictions for commercial purposes in the product facts.
Which voices are available for self-publishing?
Eight voice presets are available: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. Voices are based on licensed recordings from LibriTTS-R and LibriVox. Each voice can speak any of the 23 supported languages. All generated files carry an inaudible synthetic speech watermark.
Can I generate text to speech Hindi free of charge?
Hindi is a supported language. Free generation is possible using the $0.50 Google trial credit. Email-based accounts start without free credit. The rate is $0.01 per 1,000 characters. Failed requests are free. You must pay via USDT for additional usage after the trial.
How does the pricing scale for large catalogs?
Pricing is transparent and per-character: $0.01 per 1,000 characters. There are no volume discounts or tiered rates. Spaces and punctuation count as characters. Requests are processed sequentially, so longer texts may take time. There are no minimum spend requirements or monthly fees.
Is the free text to speech AI realistic enough for professional use?
Voices are based on licensed recordings from LibriTTS-R and LibriVox. Each file carries an inaudible watermark marking it as synthetic speech. The API supports 23 languages and 8 distinct voice presets. Speed is roughly real-time for long texts. Specific realism metrics are not provided.
Do I need an API key to use the free tier?
Yes. You must sign up on the /get-api-key/ page to receive a Bearer token. The key is required for all API requests, including the free trial. You can issue a new key at any time, which invalidates the old one immediately.
What happens if a synthesis request fails?
If synthesis fails, the charge is returned in full. Failed requests are free. This applies to both trial credit and paid balance. The API returns the error status, allowing you to retry or adjust parameters like text length or voice selection.
Are there hidden fees in the text to speech AI free offer?
No. Pricing is strictly $0.01 per 1,000 characters. Failed requests are free. There are no monthly plans, seats, or minimum spends. Top-ups via USDT (TRC-20) are automatic. No invoices with VAT are generated. The only cost is the character usage beyond any trial credit.
How long does the free trial last?
The free trial credit is valid for 7 days. It is granted only when signing in with Google. Email-based accounts do not receive this trial credit. The balance does not expire after the trial period, but the initial free credit does.
Can I use the generated audio for YouTube videos?
Yes. The API generates audio files that you receive directly. Input text is not used for training. Generated audio is not stored by the service. There are no stated restrictions on commercial use or platform integration like YouTube in the product facts.
What is the maximum text length per request?
The maximum input text length is 4096 characters per request. For longer texts, split the input into parts of up to 4096 characters. Join the resulting audio files manually. Requests are processed sequentially, so large volumes may require queuing time.
Is customer support available for free tier users?
Support is available by email only. There is no phone number or live chat. Support is not distinguished between free and paid tiers in the facts. There is no SLA or uptime guarantee. Response times are not specified.
First request
curl
curl https://api.playp94.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 Voiceover for Self-Publishing
LingvoRead enables independent publishers to automate audiobook narration by sending text to a cloud API and receiving synthesized audio files. This approach eliminates the need for recording studios or voice actors, allowing creators to generate content at scale using standard HTTP requests.
Scalable API Integration
Our endpoint accepts JSON bodies identical to the OpenAI speech format, allowing startups to integrate directly using existing SDKs. By adjusting the base URL, teams can route up to 60 requests per minute, ensuring consistent throughput for batch processing of chapters or short stories.
- Standard JSON request shape
- OpenAI SDK compatibility
- 60 requests/minute limit
Cost-Effective Volume Production
Pricing is strictly per character at $10 per million characters, with no monthly fees or seat limits. This model ensures that production costs remain proportional to content volume, making it viable for self-publishers managing tight budgets without enterprise overhead or minimum spend requirements.
- $10 per 1M characters
- No monthly fees
- Proportional pricing
Multi-Language Localization
Generate audiobooks in 23 languages, including major European and Asian markets, using the same voice presets. The API guesses language from the script but allows explicit ISO code setting, ensuring accurate pronunciation for localized content without manual voice selection for each region.
- 23 supported languages
- Automatic language detection
- Explicit ISO code support
Technical Specifications
Use the OpenAI SDK by changing the base URL to https://api.playp94.com/v1. Support multiple formats including MP3, WAV, and FLAC. Generation speed is roughly real-time, processing approximately 25 characters of text per second, with requests handled sequentially.
- OpenAI SDK compatible
- Formats: MP3, WAV, FLAC
- Real-time generation speed
Pricing Structure
Cost is $10 per million characters, with spaces and punctuation counting toward the total. Failed requests incur no charge, ensuring you only pay for successful synthesis. Accounts start with a $0.50 free trial valid for 7 days upon Google sign-in.
- $10 per 1M characters
- Failed requests are free
- $0.50 free trial
Reliability and Infrastructure
The system processes requests sequentially, which may introduce queue times under load. Rate limits are set at 60 requests per minute per key (10 per minute before the first top-up). We do not provide SLA guarantees or uptime assurances.
- 60 requests/minute limit
- Sequential processing
- No SLA guarantees
Data Privacy Standards
Input text is used solely for audio generation and is not used for training models. Generated audio is returned in the response and not stored on our servers. Request metadata is retained only for billing purposes.
- Input text not used for training
- No persistent audio storage
- Metadata kept for billing
Integration Workflow
Sign up at /get-api-key/ to receive a Bearer token. Send a POST request to the /v1/audio/speech endpoint with your text and desired voice. The API returns the audio file directly, enabling immediate integration into publishing workflows.
- Bearer token authentication
- POST /v1/audio/speech endpoint
- Instant key generation
Why Choose P94
LingvoRead offers independent infrastructure with direct API access, avoiding vendor lock-in. We provide transparent per-character pricing and a focus on precise voice synthesis for audiobook creators who require reliability without enterprise complexity.
- Independent infrastructure
- Direct API access
- No vendor lock-in
Voice Catalog for Narration
LingvoRead provides eight distinct voice presets engineered for professional audiobook production. Each voice is derived from licensed LibriTTS-R recordings, ensuring a consistent and reliable narrative baseline for independent publishers. The catalog includes four female and four male voices, allowing precise tonal matching for diverse genres.
Female Presets: Aria, Nova, Luna, Sage
The female selection offers varied narrative tones. Aria delivers a warm, clear narrator style suitable for fiction. Nova provides a bright, upbeat delivery for light non-fiction. Luna excels in soft, storytelling contexts, while Sage offers a calm, instructional tone ideal for educational content.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
Male Presets: Felix, Milo, Atlas, Orion
Male voices cover commercial to documentary needs. Felix is energetic and suited for promotional material. Milo provides a friendly, conversational style. Atlas delivers a neutral, news-like delivery, and Orion offers a deep, documentary tone for serious or historical subjects.
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
Distinct Narration Styles
Each voice maintains a specific character throughout generation. This consistency supports long-form audiobooks where tone must remain stable across chapters. All voices support 23 languages, allowing creators to maintain distinct character voices across localized editions without re-recording.

Supported Languages for Global Reach
LingvoRead supports 23 languages, covering major European and Asian markets including English, French, German, Japanese, and Chinese. This enables independent publishers to localize audiobooks efficiently without managing multiple voice providers. The API handles diverse scripts with consistent quality across all supported regions.
Major European and Asian Markets
Our infrastructure delivers precise synthesis for high-demand languages such as Spanish, Italian, and Korean. Startups can automate content localization for these primary markets, ensuring consistent voice quality across regional editions. This reduces production time for multi-language audiobook releases significantly.
- Full support for English, French, German, Japanese, Chinese, and Spanish
- Consistent audio quality across all major European and Asian languages
- Ideal for rapid localization of self-published titles
Arabic, Hebrew, and Swahili Support
Arabic, Hebrew, and Swahili are supported languages, expanding reach into emerging markets. These languages are fully integrated into the core engine, allowing creators to target diverse global audiences without requiring specialized third-party services. Each voice is optimized for natural phonetic rendering in its respective language.
- Native-quality synthesis for Arabic, Hebrew, and Swahili
- Support for right-to-left script languages
- No additional configuration required for these regions
Automatic Language Detection
The API automatically detects the language from the input text script. If the language is not specified, Latin script defaults to English. For non-English Latin-script text, you must explicitly set the language field to ensure accurate pronunciation and prosody.
- Automatic detection from input text script
- Latin script defaults to English if unspecified
- Explicit
languageparameter recommended for non-English Latin text
Technical Specifications
The API endpoint accepts standard JSON payloads, allowing developers to utilize official OpenAI SDKs by simply adjusting the base URL to https://api.playp94.com/v1. This ensures compatibility with existing integrations while maintaining our specific request shape for text-to-speech synthesis.
OpenAI SDK Compatibility
Developers can leverage existing codebases by pointing the OpenAI SDK’s base_url parameter to our API domain. The request structure mirrors the standard speech endpoint, requiring only a valid Bearer token for authentication and the appropriate model selection (tts-1 or tts-1-hd). This minimizes integration overhead for teams already familiar with standard TTS workflows.
- Standard JSON request body
- Compatible with official OpenAI SDKs
- Single active API key per account
Multiple Audio Formats (MP3, WAV, FLAC)
The system supports five output formats: mp3, wav, opus, flac, and pcm. This flexibility allows audiobook publishers to select the optimal balance between file size and fidelity. WAV and FLAC are suitable for archival master files, while MP3 and OPUS provide efficient delivery for streaming or distribution platforms.
- MP3, WAV, OPUS, FLAC, PCM
- Optimized for archival and distribution
- No proprietary format lock-in
Real-Time Generation Speed
Generation speed approximates real-time, processing roughly 25 characters of text per second for long-form content. Short phrases may take a few seconds to synthesize due to initialization overhead. Requests are processed sequentially, meaning under high load, additional requests may enter a queue before processing begins.
- ~25 characters per second
- Sequential request processing
- Queued during high load
Pricing Structure
LingvoRead utilizes a straightforward per-character billing model, charging $10 per million characters processed. This structure eliminates recurring subscription costs, allowing independent publishers to scale audio production directly in proportion to their output volume without administrative overhead.
$10 Per Million Characters
The base rate is $0.01 per 1,000 characters, including spaces and punctuation. Failed requests incur no charge, with any applied credits returned immediately. A free trial provides $0.50 in credit for seven days upon Google sign-in.
- $10 per 1,000,000 characters
- $0.01 per 1,000 characters
- Failed requests are free
- $0.50 trial credit (7 days)
No Monthly Fees or Seats
There are no monthly plans, seat limits, or minimum spending requirements. Balances do not expire, and top-ups via USDT (TRC-20) are processed automatically within minutes, ensuring continuous availability for production workflows.
- No monthly subscriptions
- No seat limits
- No minimum spend
- Balances never expire
Transparent Character Counting
All characters, including spaces and punctuation, are counted toward the total. Each request supports up to 4,096 characters, allowing for precise cost estimation per audiobook chapter or localized segment.

Reliability and Infrastructure
P94 Audio operates on a shared cloud infrastructure optimized for text-to-speech synthesis. Requests are processed sequentially, ensuring deterministic output but requiring awareness of concurrency limits. The system handles volume efficiently without dedicated dedicated servers, keeping overhead low for independent publishers.
60 Requests Per Minute Limit
Each API key supports a maximum of 60 requests per minute. New accounts starting with the free trial credit are limited to 10 requests per minute until the first top-up is processed. This limit applies uniformly regardless of text length or voice selection.
Automatic Queue Management
Requests exceeding the per-minute threshold are placed in a processing queue. They are executed in the order received. Since synthesis is processed sequentially, high-volume jobs may experience latency during peak usage periods. Users should monitor their request rate to avoid queuing delays.
No SLA Guarantees
We do not provide a Service Level Agreement (SLA) or uptime guarantee. Infrastructure is maintained for reliability but operates without enterprise-grade contracts. Downtime or performance variations do not trigger automatic credits. For critical production pipelines, implement retry logic in your integration.
Data Privacy Standards
LingvoRead processes input text exclusively for the purpose of generating the requested audio output. This text is not retained for model training or used to improve future voice synthesis models, ensuring that your manuscript content remains proprietary.
Input Text Not Used for Training
Unlike many consumer-grade services, we do not ingest your submitted text into our training datasets. The content you provide is used solely to produce the immediate audio file and is discarded after the synthesis process completes, unless required for billing verification.
No Persistent Audio Storage
Generated audio files are returned directly in the API response and are not stored on our servers. Once you download the file, LingvoRead retains no copy of your synthesized speech, ensuring that your final audio assets remain under your direct control.
Metadata Retention for Billing
We retain minimal request metadata, including timestamp, character count, and status, solely for accurate billing and troubleshooting. This data does not include the audio content or the source text, ensuring that your usage patterns are transparent and limited to administrative necessity.
Integration Workflow
LingvoRead operates on independent infrastructure, ensuring your synthesis workload is not subject to the capacity constraints or pricing shifts of major cloud providers. The system processes requests sequentially, which may introduce queue times under load.
Simple JSON Endpoint
Send a POST request to the /v1/audio/speech endpoint with a JSON body containing the model, input text, voice, and format. The request shape mirrors the OpenAI speech endpoint, allowing standard HTTP libraries to handle transmission without custom parsers.
- Endpoint: POST https://api.playp94.com/v1/audio/speech
- Body: JSON with model, input, voice, response_format, speed
Bearer Token Authentication
Include your API key in the Authorization header as a Bearer token. Each account maintains one active key; issuing a new key immediately invalidates the previous one, ensuring strict access control.
- Header: Authorization: Bearer tts-...
- Single active key per account
Instant Key Generation
Generate your API key immediately upon signing in via Google or email. The dashboard displays your key, balance, and usage statistics, enabling you to begin testing synthesis requests within minutes of account creation.

Why Choose P94
P94 operates on independent infrastructure, ensuring your synthesis workload is not subject to the capacity constraints or pricing shifts of major cloud providers. This autonomy provides consistent performance for audiobook production pipelines.
We offer direct API access with no intermediary layers, allowing for straightforward integration into your existing content management or localization systems.
Independent Infrastructure
Our dedicated servers handle synthesis requests without sharing resources with unrelated services, ensuring predictable latency for bulk audiobook generation.
- Dedicated processing resources
- Independent scaling
Direct API Access
Connect directly to the endpoint without proxy overhead. Use standard OpenAI SDKs by adjusting the base URL for immediate integration.
- Standard JSON endpoints
- OpenAI SDK compatible
No Vendor Lock-In
We do not require proprietary libraries or custom formats. Your integration relies on standard HTTP requests and common audio codecs, allowing easy migration if needed.
Accounts are per site with simple key management, ensuring you retain full control over your authentication and usage data.
- Standard HTTP/JSON
- Standard audio formats
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Self-publishing lets startups directly monetize their expertise by producing audiobooks for global audiences.
23 languages
Any voice speaks any of these languages.
Sources and further reading
- Wikipedia
- IETF RFC 7845: Ogg Opus
- Python documentation
- ISO 639 language codes
- Creative Commons Attribution 4.0
- TRON developer hub: TRC-20
- MDN: Web Speech API
- OpenAI API reference: create speech
- FFmpeg documentation
- LibriVox public-domain audiobooks
- W3C WAI: making audio and video accessible
- openai-node on GitHub
