Frequently asked questions
Is this a dedicated French TTS engine?
No. AuraCast is a cloud text-to-speech API supporting 23 languages, including French. Any of the eight voice presets can speak French. You specify the language via an optional ISO code parameter. If omitted, the system guesses the language from the script, defaulting to English for Latin text.
Which voice is best for French radio ads?
Select from eight presets: aria, nova, luna, sage, felix, milo, atlas, or orion. For energetic promotions, use felix. For calm, instructional content, use sage. All voices support French natively. Choose based on your campaign tone, as all voices deliver consistent synthetic speech optimized for commercial use.
Can I use the audio for commercial campaigns?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Generated files carry an inaudible watermark marking them as synthetic speech. Input text is not used for training, ensuring your content remains distinct for your advertising campaigns.
How many characters can I send per request?
You can send up to 4096 characters per request. For longer texts, split them into parts of this limit and join the resulting audio files. Spaces and punctuation count toward the character total. This limit applies to all models, including tts-1 and tts-1-hd.
Does the API support speed adjustments for French?
Yes. You can adjust the speech speed between 0.25 and 4.0 for any supported language, including French. This allows you to optimize pacing for radio spots or localized content. The speed parameter is included in the JSON body of your POST request to the speech endpoint.
Are the voices based on human recordings?
Yes. All eight voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. Each generated audio file includes an inaudible watermark that identifies it as synthetic speech, distinguishing it from original human recordings while maintaining high quality.
What happens if a request fails?
Failed requests are free. If synthesis fails, the charge is returned in full. This ensures you only pay for successful audio generation. Request metadata, such as time and status, is retained for billing purposes, but no credit is deducted for unsuccessful attempts.
Do I need an OpenAI account to use this?
No. You sign up directly on km12.info using Google or email. The API mimics the OpenAI request shape, allowing you to use OpenAI SDKs by changing the base URL to https://api.km12.info/v1. You do not need an existing OpenAI account or subscription to use AuraCast.
How is the language detected for French text?
If you do not set the optional language parameter, the system guesses the language from the script. Latin script text defaults to English. For French text in Latin script, you should explicitly set the language parameter to ensure accurate synthesis and avoid incorrect language detection.
Is there a limit on the number of requests per minute?
Yes. The rate limit is 60 requests per minute per key. Before your first top-up, the limit is 10 requests per minute. Requests are processed sequentially, so under load, a request may wait in a queue. This applies to all accounts regardless of plan.
Can I mix different voices in one audio file?
No. Each request generates audio for a single voice. To mix voices, you must send separate requests for each voice segment and join the resulting audio files. The API does not support mixing multiple voices within a single response payload or audio file.
What audio formats are supported for broadcast?
You can choose from mp3, wav, opus, flac, and pcm formats. These formats are suitable for various broadcast and digital advertising needs. Specify your preferred format in the response_format field of your request. All formats are generated with consistent synthetic voice quality.
Is there a minimum spend requirement?
No. There are no monthly plans, seats, or minimum spend requirements. You pay $10 per million characters. Top-ups via USDT on TRON have a minimum of $5. Balance does not expire, and you only pay for the characters you actually use.
How long does the free trial last?
The free trial provides $0.50 of credit, valid for 7 days. This covers approximately 50,000 characters. The trial is available when you sign in with Google. Accounts created with email and password start without this trial credit.
First request
curl
curl https://api.km12.info/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.mp3API Overview
AuraCast provides a cloud-based Text-to-Speech API designed for advertising agencies and startups producing localized radio spots. The core endpoint accepts text and returns synthesized audio files, eliminating the need for on-premise infrastructure or enterprise-level overhead.
By standardizing on the OpenAI SDK request shape, integration is straightforward. Teams can adapt existing codebases by changing the base URL, enabling rapid deployment of synthetic voice content for global campaigns without learning proprietary protocols.
Cloud-based synthesis endpoint
The API endpoint POST https://api.km12.info/v1/audio/speech processes JSON payloads and returns audio files. Input text is limited to 4096 characters per request; longer texts must be split into parts and joined by the client.
- Endpoint: POST /v1/audio/speech
- Auth: Bearer token (tts-...)
- Rate limit: 60 requests/minute
OpenAI SDK compatibility
The request structure mirrors the OpenAI speech endpoint. Developers can use official OpenAI SDKs by setting the base URL to https://api.km12.info/v1 and providing the AuraCast API key.
Real-time audio generation
Audio is generated synchronously. Typical speed is roughly real-time (25 characters per second). Short phrases take a few seconds; longer texts may queue under load but process sequentially.
Voice Profiles
AuraCast provides eight distinct voice presets designed for commercial clarity and broadcast readiness. Each voice is engineered for specific tonal requirements, ensuring consistent synthetic speech optimized for advertising and localized content without enterprise overhead.
Female presets: Aria, Nova, Luna, Sage
Aria offers a warm, clear narrator style. Nova delivers a bright, upbeat tone ideal for energetic promotions. Luna provides a soft, storytelling voice. Sage provides a calm, instructional voice.
- Aria: warm, clear narrator
- Nova: bright, upbeat
- Luna: soft, storytelling
- Sage: calm, instructional
Male presets: Felix, Milo, Atlas, Orion
Felix is energetic and suited for promos. Milo offers a friendly, conversational tone for direct-to-consumer messaging. Atlas provides a neutral, news-style delivery for factual content, and Orion delivers a deep, documentary voice for authoritative brand statements.
- Felix: energetic, promo
- Milo: friendly, conversational
- Atlas: neutral, news
- Orion: deep, documentary
Licensed source recordings
All voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), derived from LibriVox public-domain audiobook readings. This foundation ensures high-quality synthetic speech while maintaining clear provenance for commercial use cases.
Language Support
AuraCast delivers text-to-speech synthesis for French and other languages, supporting production of localized content.
French voice synthesis
Our API handles complex French phonetics and prosody natively, ensuring natural-sounding audio for marketing campaigns. Any voice can speak any of the supported languages.
23 supported languages
Beyond French, the API supports 23 languages including Arabic, Chinese, German, Hindi, Japanese, Korean, Portuguese, Russian, Spanish, and Turkish. This allows agencies to produce multi-market campaigns using a single integration, reducing development time and infrastructure complexity.
Automatic language detection
The system automatically detects the input script when the language field is omitted, defaulting to English for Latin script. For non-English Latin text, explicitly setting the language parameter ensures accurate pronunciation and avoids misinterpretation by the engine.
Audio Formats
Audio generation supports multiple output formats to suit different distribution channels. The API returns synthesized speech as standard audio files, allowing seamless integration into existing media pipelines for web and broadcast delivery.
MP3 for web streaming
MP3 is one of the supported formats. It provides a balance between file size and audio quality, making it ideal for embedding in HTML5 players or serving via CDN for global ad campaigns.
WAV for broadcast
WAV offers uncompressed audio. This format ensures no data loss during transmission, meeting standard requirements for traditional media distribution and high-fidelity playback systems.
Opus and FLAC options
Opus provides high-quality compression for low-bandwidth environments, while FLAC offers lossless compression for archival purposes. Both formats allow flexible storage and processing choices depending on your specific infrastructure needs.
Speed Control
Adjust the speech rate between 0.25x and 4.0x to match specific production needs. This parameter allows precise control over the pacing of generated audio files without altering the voice character.
Adjustable rate 0.25x–4.0x
The speed parameter accepts values from 0.25 to 4.0. This range accommodates everything from slow, deliberate instruction to rapid-fire promotional announcements. Adjustments are applied during synthesis, ensuring consistent audio quality across all rates.
Optimized for radio pace
Default settings align with standard commercial narration speeds. This ensures radio spots and advertising content maintain professional pacing without requiring manual editing. The engine processes requests sequentially, maintaining consistent timing.
Standard narration speed
Standard speed approximates real-time generation, processing roughly 25 characters per second. For longer texts, the API splits input into 4096-character segments. This ensures stable delivery even under load.

Technical Integration
AuraCast integrates directly into your production pipeline using standard HTTP requests. The API accepts simple JSON payloads containing your text, selected voice, and desired audio format, returning the synthesized audio file directly in the response body.
Simple JSON payload
Send text via a POST request to https://api.km12.info/v1/audio/speech. The body requires only the model, input text, and voice preset. Optional fields like speed (0.25–4.0) allow you to adjust narration pace for radio spots or e-learning modules without external processing.
Bearer token authentication
Include your unique API key in the Authorization header as Bearer <your-key>. Each account holds one active key; issuing a new key immediately invalidates the previous one, ensuring strict security for your advertising agency’s billing and usage data.
Standard error handling
Failed synthesis requests incur no charge, with the credit returned immediately. The API returns standard HTTP status codes (200 for success, 4xx/5xx for errors) allowing your system to retry or log failures accurately without complex parsing logic.
Use Cases
AuraCast enables agencies to produce localized radio spots at scale. By integrating our TTS API, teams generate consistent synthetic voices optimized for commercial use without enterprise overhead. This eliminates the logistical costs of booking talent for every regional variation.
The infrastructure delivers reliable audio files via standard HTTP endpoints, allowing seamless integration into existing campaign workflows. With support for 23 languages, brands can deploy identical messaging across diverse markets using a single, unified voice profile.
Radio spot production
Generate localized radio spots efficiently. Use presets like Felix for energetic promos or Atlas for neutral news reads. Split texts over 4,096 characters to maintain audio quality. Each request returns a stable audio file ready for broadcast integration.
- Supports 23 languages including French, German, and Spanish
- Adjustable speed from 0.25x to 4.0x for precise pacing
- No voice cloning required; use licensed LibriTTS-R presets
E-learning modules
Create multilingual educational content quickly. Select Sage for calm instruction or Luna for storytelling. The API handles text splitting automatically, ensuring continuous audio for longer lessons. Ideal for scaling training materials across global teams.
- Consistent tone across multiple language variants
- Optimized for clear narration and instructional pacing
- Fast turnaround for bulk content generation
Accessibility compliance
Meet WCAG standards by converting text to speech instantly. Use Aria or Nova for clear, readable audio. The synthetic watermark identifies generated content. Ensure your digital assets are accessible without hiring specialized voice actors for every update.
- Instant text-to-speech conversion
- Supports standard audio formats (MP3, WAV)
- Transparent billing per character used
Pricing Model
Charge only for what you use. The rate is $10 per 1 million characters, equating to $0.01 per 1,000 characters. Spaces and punctuation count toward the total. Failed requests are free, with the charge returned in full.
Pay per character
Your cost scales directly with volume. At standard speed, roughly 25 characters generate one second of audio. This linear model ensures predictable expenses for high-volume radio spot production without hidden fees for processing time.
- $10 per 1 million characters
- $0.01 per 1,000 characters
- Sites and punctuation count as characters
No monthly fees
Unlike enterprise contracts, there are no minimum spends, seats, or subscription tiers. The balance does not expire. You maintain full control over cash flow by topping up only when necessary.
Transparent billing
Top-ups are processed via USDT on the TRON network (TRC-20). Minimum deposit is $5, with automatic crediting within minutes. Request metadata, including time and status, is retained for accurate billing records.
Getting Started
Create your account via the /get-api-key/ page using Google or email. A $0.50 trial credit activates immediately for Google sign-ups, covering approximately 50,000 characters for seven days. Email accounts begin with zero balance and require a top-up.
Google sign-up bonus
Sign up at /get-api-key/ with your Google account. The system credits $0.50 instantly, valid for 7 days. This allows immediate testing without payment details.
- Instant $0.50 credit
- No payment method required
- Valid for 7 days
API key generation
Your dashboard displays a single active Bearer token. Generate a new key at any time; the previous key becomes invalid immediately. Use this key for authentication in all requests.
- One active key per account
- Instant invalidation of old keys
- Format: Bearer tts-...
First request example
Send a POST request to https://api.km12.info/v1/audio/speech. Include your model, input text, voice selection, and Bearer token. The API returns audio data directly in the response.
- Endpoint: POST /v1/audio/speech
- Auth: Bearer token
- Format: JSON body
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. This ensures that your radio spots maintain the same tonal quality and pacing across all episodes and campaigns.
23 languages
Any voice speaks any of these languages.
