Frequently asked questions
What is a voice cloning API?
A voice cloning API generates synthetic speech from text using pre-recorded voice presets. It is not a custom cloning service where you upload a unique voice sample. Instead, it uses licensed recordings from sources like LibriVox to produce broadcast-ready audio files via a simple API endpoint.
How does voice cloning differ from standard TTS?
Our service is a standard Text-to-Speech API using fixed voice presets like Aria or Felix. It does not offer custom voice cloning where you train a model on your own audio. Standard TTS converts text to speech using these established, licensed voice profiles without requiring additional voice training data.
Can I use the voices for commercial radio ads?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. This makes them suitable for commercial use in radio spots and audio advertising. Each generated file also carries an inaudible watermark to identify it as synthetic speech.
Do you offer custom voice cloning?
No. We do not offer custom voice cloning, voice design, or the ability to upload your own voice. You must choose from the eight available presets. If you need a specific voice, you must select the closest matching preset from our library rather than creating a new one.
Which voices are best for promotional spots?
Q: Which voices are suitable for promotional spots? A: Felix offers an energetic tone ideal for promos, while Nova provides a bright, upbeat delivery. Milo is friendly for conversational ads, and Sage is calm for instructional content. Each voice has a distinct character suitable for different advertising styles, from news to storytelling.
How many languages are supported?
We support 23 languages, including English, Spanish, German, French, Japanese, and Chinese. If the language is not specified, the system guesses it from the script, defaulting to English for Latin text. You should manually set the language for non-English Latin-script text to ensure accuracy.
What audio formats are available?
You can request audio in mp3, wav, opus, flac, or pcm formats. These formats allow flexible integration into your production workflow. The API returns the audio file directly in the response, ensuring you receive the exact format you need for your radio or digital ad campaigns.
Is there a free trial available?
Yes, signing in with Google provides $0.50 of credit, valid for 7 days. This covers approximately 50,000 characters. Accounts created with email and password start without trial credit. You can test the API quality and workflow before committing to a top-up via USDT.
How fast is the synthesis process?
Synthesis takes roughly real time, about 25 characters of text per second of audio. Short phrases may take a few seconds, while longer texts are split and joined. Requests are processed sequentially, so high load may cause queuing delays, but typical speed matches real-time generation.
Do I need to set the language manually?
It is recommended to set the language manually, especially for non-English Latin-script text. If omitted, the system guesses the language, defaulting to English. Explicitly setting the ISO code ensures the correct voice model is used, preventing mispronunciations in languages like Arabic, Chinese, or Russian.
Are the voices based on real people?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. These are real human voices recorded for public domain projects. The generated audio carries an inaudible watermark to mark it as synthetic speech derived from these licensed sources.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are only billed for successful requests. Failed requests do not incur any cost, ensuring you only pay for usable audio files. This protects your budget during testing or if temporary errors occur during processing.
How do I pay for the API?
Payment is via USDT on the TRON network (TRC-20) only. The minimum top-up is $5, credited automatically within minutes. There are no cards, PayPal, subscriptions, or invoices. Balance does not expire, and pricing is $0.01 per 1,000 characters, with no monthly plans or seats.
Can I change my API key?
Yes, you can issue a new API key at any time from your account dashboard. When a new key is issued, the old one stops working immediately. This allows you to rotate keys for security or manage access without downtime, ensuring your advertising workflows remain secure.
First request
curl
curl https://api.ah777.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.mp3Broadcast-Ready Synthetic Voices
SpotLogic delivers broadcast-ready synthetic voices grounded in licensed sources, eliminating the need for complex voice talent negotiations or union rates. Every generated file carries an inaudible watermark that marks it as synthetic speech, ensuring clear provenance for your radio spots.
Licensed Voice Sources
Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0), originating from LibriVox public-domain audiobook readings. This foundation ensures a clear licensing path for commercial advertising use without the overhead of individual talent contracts.
Inaudible Watermarking
Each audio file includes an inaudible watermark identifying it as synthetic speech. This provides transparency and helps distinguish AI-generated content in broadcast environments.
8 Distinct Presets
Choose from eight distinct presets tailored for advertising needs. Options range from warm narrators like Aria to energetic promo voices like Felix, covering neutral news tones with Atlas or deep documentary styles with Orion.
- 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
Built for Agency Workflows
Our API is engineered to integrate seamlessly into existing ad tech stacks. By mirroring the OpenAI speech endpoint structure, your engineering team can switch providers without rewriting code, simply by updating the base_url in the official OpenAI SDKs.
This compatibility ensures that your current automation pipelines for radio spot generation remain stable. You can leverage familiar tools and libraries to manage voice selection and audio delivery within your agency’s standard workflow.
We use a straightforward JSON structure for all requests. There is no need to learn a proprietary format or manage complex header configurations. This simplicity reduces integration time and minimizes the risk of errors during the handoff between creative and technical teams.
OpenAI SDK Compatibility
Our API mirrors the OpenAI speech endpoint structure, allowing your team to use the official OpenAI SDKs with a simple base_url change. This means your existing automation scripts for radio spot generation require minimal adjustment to switch providers.
This compatibility ensures that your current engineering pipelines remain stable. You can leverage familiar tools to manage voice selection and audio delivery without overhauling your tech stack.
- Works with official OpenAI SDKs
- Only
base_urlneeds changing - No proprietary format required
Simple JSON Requests
Requests use a clean JSON body containing model, input, voice, and response_format. There are no complex headers or nested parameters to manage. This straightforward structure reduces integration time and minimizes errors during the handoff between creative and technical teams.
You can test endpoints directly with curl or any HTTP client. The consistency across endpoints simplifies debugging and ensures reliable delivery of audio files to your production servers.
- Standard JSON body
- Minimal parameters
- Easy to debug
Fast Synthesis Speed
Long texts generate at roughly real-time speed (25 characters per second). Short phrases take a few seconds to process. This speed allows for iteration on spot scripts, though requests are processed sequentially and may queue under load.
Requests are processed sequentially, so under heavy load, a request may wait in a queue. However, for typical agency volumes, this ensures consistent quality and predictable timing for your ad deliveries.
- Real-time speed for long texts
- Few seconds for short phrases
- Sequential processing
Global Reach with Local Voices
Reach audiences across 23 markets with voices that adapt to local speech patterns. Our 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.
23 Supported Languages
Every voice can speak any of these languages, ensuring consistent quality whether you are producing a spot for Tokyo or São Paulo. This eliminates the need for multiple voice providers when expanding your agency’s geographic reach.
- Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, Turkish
Automatic Language Detection
If you do not specify a language, the system guesses it from the script. Latin script text defaults to English, which handles standard English copy without extra configuration.
Manual Language Override
For non-English Latin-script text, always set the language field to ensure correct pronunciation. This prevents the default English bias from affecting accents or intonation in languages like Dutch or German.
Transparent Pricing for Spots
SpotLogic charges a flat $10 per one million characters processed, including spaces and punctuation. This per-character model ensures predictable costs for radio spots of any length.
Per-Character Billing
The cost is strictly tied to input text length. At $0.01 per 1,000 characters, you pay only for what is sent to the synthesis engine. Longer scripts are split internally, but the rate remains constant regardless of total duration or file size.
- $10 per 1,000,000 characters
- $0.01 per 1,000 characters
- Spaces and punctuation count
No Hidden Fees
There are no monthly plans, seats, or minimum spend requirements. Failed requests are free, with charges returned in full if synthesis fails. No invoices with VAT or subscription renewals complicate the billing cycle.
Trial Credit Available
Signing in with Google provides $0.50 in trial credit, valid for 7 days. This allows agencies to test voice quality and integration without immediate payment. Email-based accounts start with zero credit until a top-up is made.
Technical Specifications
The API delivers audio in MP3, WAV, Opus, FLAC, and PCM formats, allowing agencies to select the optimal codec for broadcast pipelines or digital distribution. Each request returns a direct audio file without requiring external processing.
Multiple Audio Formats
Select the output format via the response_format parameter. MP3 and Opus are efficient for web delivery, while WAV and FLAC preserve lossless quality. PCM is available for raw data processing.
- MP3, WAV, Opus, FLAC, PCM
Speed Control
Adjust speech rate between 0.25x and 4.0x using the speed parameter. This allows precise timing adjustments for radio spots without re-recording, ensuring tight fit within fixed ad slots.
Character Limits
Each request supports up to 4096 characters. For longer scripts, split the text into chunks and join the resulting audio files. Short phrases typically generate in a few seconds, while longer texts approach real-time speed.

Licensing and Rights
Our voice models are built on licensed recordings from the LibriTTS-R dataset, ensuring a clear legal foundation for commercial advertising use. Each generated audio file contains an inaudible watermark, marking it as synthetic speech and providing an additional layer of transparency for broadcasters and platforms.
The underlying data derives from LibriVox public-domain audiobook readings, licensed under CC BY 4.0. This basis allows us to offer synthetic voices with predictable licensing terms, suitable for radio spots and audio ads.
You can use the generated audio commercially. The voices are distinct presets, not imitations of specific celebrities or public figures, reducing the risk of likeness disputes in your campaigns.
LibriTTS-R Foundation
The voices are based on licensed recordings from the LibriTTS-R dataset. This foundation ensures synthetic speech suitable for advertising contexts.
- Based on professional-grade speech data
- Trained on diverse speaker samples
- Optimized for synthetic voice quality
CC BY 4.0 Basis
The source audio originates from LibriVox public-domain readings, licensed under Creative Commons Attribution 4.0 International. This permissive license allows for commercial use and modification, forming the legal bedrock of our TTS engine’s voice models.
- Public domain source recordings
- CC BY 4.0 licensed
- Commercial use permitted
Commercial Use Allowed
All generated audio files are cleared for commercial advertising use. You retain the rights to the final audio output produced via the API for your specific campaigns.
- No additional licensing fees
- Suitable for broadcast ads
- Clear commercial rights
Integration Guide
Begin by generating your API key on the /get-api-key/ dashboard. Pass this key as a Bearer token in the Authorization header of every request. Each account holds one active key; issuing a new one immediately invalidates the previous version.
API Key Setup
Ensure your key starts with 'tts-' and is sent via Authorization: Bearer <key>. One active key per account keeps access simple. Revoke and regenerate instantly if needed.
First Request Example
Send a POST request to https://api.ah777.info/v1/audio/speech with a JSON body. Include the model, input text, voice, and response_format. The API returns the audio file directly.
- Endpoint: POST /v1/audio/speech
- Auth: Bearer token
- Body: JSON with model, input, voice
SDK Configuration
Use the official OpenAI SDKs by setting the base URL to https://api.ah777.info/v1. This allows you to use standard methods like Audio.speech.create without rewriting your client logic.
Support and Contact
SpotLogic offers straightforward support for advertising agencies integrating synthetic voices into their production pipelines. We focus on clear, direct assistance without the complexity of phone trees or live chat queues.
Our support channel is dedicated to resolving technical and billing questions efficiently, ensuring your audio ad campaigns remain on schedule.
Email Support
All inquiries are handled via email. There is no phone number or live chat option, keeping our communication channel simple and asynchronous.
- Direct email support for all account and technical questions
- No phone number or live chat available
Documentation
Comprehensive guides are available at /docs/ to help you configure the API correctly. The documentation covers endpoint structures, authentication, and common workflows.
- Full API reference with JSON body examples
- Configuration guides for OpenAI SDK compatibility
FAQ Section
Common questions about pricing, character limits, and voice selection are addressed in our FAQ. Review this section before contacting support for quick answers.
- Answers to frequent billing and technical queries
- Guidance on voice selection and language settings
Why Agencies Choose Us
SpotLogic removes the friction of recurring billing cycles. You pay only for the characters you generate, with no monthly plans, seats, or minimum spend. This model aligns perfectly with the variable nature of advertising campaigns, where spot production volume fluctuates between quiet periods and launch rushes.
No Monthly Plans
There are no subscriptions to manage or cancel. Your balance never expires, allowing you to top up only when needed. This approach eliminates the waste of paying for idle capacity during the creative phase of a campaign.
Instant Top-ups
Funds are added via USDT on the TRON network (TRC-20) and credited automatically within minutes. With a minimum top-up of just $5, you can maintain production continuity without waiting for invoice processing or payment approvals. No cards or PayPal required.
Simple Scaling
Generate hundreds of spot variations overnight without complex licensing tiers. The API handles the load, processing requests sequentially with predictable timing. You scale usage directly with your output needs, from a single test read to a full campaign rollout.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Selecting the right format depends on your final distribution channel.
23 languages
Any voice speaks any of these languages.
