Frequently asked questions
Is this voice cloning technology?
No, we do not offer custom voice cloning. You select from eight preset voices based on licensed recordings from LibriTTS-R and LibriVox. Each generated file carries an inaudible watermark marking it as synthetic speech. You cannot upload your own voice or design custom voices, but the presets are optimized for natural-sounding advertising workflows.
Can I use these voices for commercial radio ads?
Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. You can use the generated audio for commercial purposes, including radio spots and advertising campaigns, without hiring expensive voice actors. The API delivers synthetic speech optimized for your ad workflows.
How much does it cost to generate a 30-second spot?
Cost depends on text length, not duration. Rates are $10 per 1 million characters. A typical 30-second spot uses roughly 125 characters (at ~25 chars/sec). This costs approximately $0.00125. Failed requests are free, and you only pay for the characters sent in successful synthesis requests.
Do you offer custom voice cloning for brands?
No. We offer eight preset voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. These are based on licensed recordings from LibriTTS-R and LibriVox. We do not allow you to upload your own voice or create custom clones. You select from the available presets to fit your brand's tone.
What languages are supported for international ads?
We support 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. Set the language parameter for non-English Latin-script text to ensure correct pronunciation.
Can I change the speed of the voice for fast reads?
Yes. You can adjust the speed between 0.25 and 4.0 using the speed parameter in your API request. This allows you to create fast-paced reads for radio spots or slower, clearer deliveries for instructional content. The default speed is 1.0. Adjustments are applied during synthesis.
Are the voices based on real human actors?
Yes. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. Each generated file carries an inaudible watermark that marks it as synthetic speech. The voices are presets, not real-time human performances, but they deliver natural-sounding results for advertising.
Do I need to pay per request or per second of audio?
You pay per character, not per second or per request. The rate is $10 per 1 million characters. Spaces and punctuation count as characters. Failed requests are free, so you only pay for successful synthesis. This model is predictable and aligns with the length of your ad copy.
What happens if my API request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures you only pay for successfully generated audio files. If you encounter issues, check your input text length and format, or contact support via email for assistance with your account.
Can I use the generated audio in YouTube ads?
Yes. The voices are based on licensed recordings from LibriTTS-R and LibriVox, suitable for commercial use. You can use the generated audio files in YouTube ads, radio spots, and other advertising media. Each file includes an inaudible watermark identifying it as synthetic speech.
Is there a limit on how many characters I can send?
Yes, each API request supports up to 4096 characters of input text. For longer texts, split them into parts of this size and join the resulting audio files. This ensures consistent quality and performance. Short phrases may take a few seconds to generate, while longer texts process at roughly real-time speed.
Do you store the audio files I generate?
No. Generated audio is returned in the response and not stored by us. Input text is used only to produce the audio and is not used for training. We keep request metadata (time, characters, status) for billing purposes, but the actual audio files are not retained on our servers.
Can I mix different voices in one project?
The API generates one audio file per request. To mix voices, generate separate audio files for each voice and combine them in your editing software. You can switch voices between requests by changing the voice parameter. This gives you full control over your project's audio composition and pacing.
How do I pay with USDT?
Top-up is done via USDT on the TRON network (TRC-20) only. The minimum top-up is $5. Credits are added automatically within minutes after your transfer. There are no cards, PayPal, or subscriptions. Balance does not expire. You can check your balance and usage on the /get-api-key/ page.
First request
curl
curl https://api.playfomo7.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.mp3Why TTS Replaces Voice Actors for Ads
Generating radio spots from script to audio in minutes replaces the weeks-long casting and booking process. Our API delivers synthetic speech optimized for advertising workflows, allowing freelancers to iterate on tone and pacing without scheduling constraints.
Unlike hiring voice actors, there are no session fees or minimum buyouts. You pay only for the characters used, making high-quality voiceovers accessible for any budget, from single spot tests to full campaign runs.
Speed vs. Human Casting
Human casting involves sourcing talent, negotiating rates, and waiting for studio availability. Our API processes requests sequentially, delivering audio files as soon as synthesis completes. This eliminates the lag between creative direction and final deliverable.
Typical generation speed is roughly real time (about 25 characters per second). Short phrases take only a few seconds, enabling rapid A/B testing of different voice tones for the same script.
Cost Efficiency for Spot Ads
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. This predictable cost structure removes the variable expense of union scale or freelance rates.
Failed requests are free, so you only pay for successful synthesis. With a $0.50 free trial credit, you can generate approximately 50,000 characters to test quality before committing to a top-up.
Consistency Across Campaigns
Human voices vary slightly between sessions and days. Our 8 presets provide identical timbre and delivery style every time, ensuring brand consistency across multiple ads and platforms.
Use the same voice for a 30-second radio spot and its 6-second social media cutdown. The uniform quality maintains professional standards without requiring re-hiring for minor variations.
Our 8 Professional Voice Presets
Choose from eight distinct voice presets. Each voice offers a unique tonal quality, allowing you to match the emotional tone of your radio spot or voiceover without the variability of human casting.
Warm Narrators (Aria, Luna)
Aria provides a warm, clear narrative tone ideal for storytelling and brand introductions. Luna offers a soft, soothing delivery perfect for emotional or lifestyle-focused spots.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling tone
Energetic Promos (Felix, Nova)
Felix delivers an energetic, promo-ready voice that grabs attention quickly. Nova adds a bright, upbeat quality suitable for dynamic product announcements.
- Felix: Energetic, promo style
- Nova: Bright, upbeat delivery
Neutral & Deep (Atlas, Orion, Milo, Sage)
Atlas ensures neutral clarity for news-style reads, while Orion provides a deep, documentary-style depth. Milo offers a friendly, conversational tone, and Sage delivers calm, instructional clarity.
- Atlas: Neutral, news-style
- Orion: Deep, documentary style
- Milo: Friendly, conversational
- Sage: Calm, instructional
How It Works for Ad Agencies
FomoVoice delivers a straightforward API endpoint that accepts your ad copy and returns a ready-to-use audio file. By sending text via a simple POST request, you receive synthesized speech without managing infrastructure or coordinating with human talent.
Send Text, Get Audio File
Your workflow begins by sending up to 4,096 characters per request. The API processes the input and returns an audio file directly in the response. If your script exceeds the limit, split it into parts and join the resulting audio files for a seamless final spot.
Real-Time Generation Speed
Generation typically runs at roughly real-time speed, producing about 25 characters of text per second. Short phrases take a few seconds to synthesize. Under heavy load, requests are processed sequentially, so longer texts may queue briefly but remain consistent.
Multiple Audio Formats
Choose from MP3, WAV, Opus, FLAC, or PCM to match your production pipeline. MP3 offers efficient compression for web delivery, while WAV and FLAC provide lossless quality. Select the format that best fits your editing software.
- MP3: Ideal for web and streaming
- WAV: Standard for broadcast editing
- Opus: High efficiency for low bandwidth
- FLAC: Lossless quality for archives
- PCM: Raw audio for processing
Languages for Global Campaigns
Reach audiences in 23 languages with a single API key. Our synthetic voices support global advertising campaigns, ensuring consistent brand tone without hiring localized talent for every region.
23 Supported Languages
Generate spots in Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Every voice preset speaks all 23 languages natively.
Default English Detection
If you omit the language field, the API guesses the language from the script. Latin-script text defaults to English, saving you a parameter for standard US or UK ad copy.
Manual Language Selection
For non-English Latin text, always set the language parameter to ensure accurate pronunciation. This prevents the default English detection from misreading French or German copy as English.
- Not supported: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, Bengali.
Pricing for Freelancers
FomoVoice charges $10 per 1 million characters, making it $0.01 per 1,000 characters. Spaces and punctuation count toward this total. Failed synthesis requests are free, ensuring you only pay for successful audio generation.
We operate on a pay-as-you-go model with no monthly fees, no seats, and no minimum spend. There are no subscriptions or invoices with VAT, keeping your overhead predictable and low for ad agency workflows.
Pay Per Character
Your balance decreases based on character count. Long radio scripts are split into 4,096-character chunks automatically. You receive the final audio file without hidden costs for processing or format conversion.
- $0.01 per 1,000 characters
- Failed requests are free
- Balance does not expire
No Monthly Fees
We do not require monthly plans or enterprise contracts. You can top up only when needed. This structure suits freelancers who generate spots intermittently rather than running constant high-volume campaigns.
- No monthly subscriptions
- No minimum spend
- No seats or licenses
Free Trial Credit
Signing in with Google grants $0.50 of credit, valid for 7 days. This allows about 50,000 characters for testing your first radio spot. Email-based accounts start without this trial credit.
- $0.50 initial credit
- 7-day validity
- Google sign-in required

Voice Cloning vs. Preset Voices
We do not offer custom voice cloning, emotion tags, or phoneme dictionaries. You cannot upload a sample of your own voice to create a unique clone, nor can you design a new voice from scratch. The system uses eight fixed presets based on licensed recordings from LibriTTS-R and LibriVox.
For ad agencies, fixed presets are often more reliable than cloning. Cloned voices can sometimes sound uncanny or inconsistent across different scripts, whereas our presets like Felix or Nova offer proven, consistent tonal qualities optimized for promotional content.
What We Don't Offer
Our API does not support custom voice cloning, emotion tags, or SSML. There is no option to upload your own audio samples to create a unique voice model. We provide eight established presets rather than building bespoke voices for each client.
Why Presets Are Better for Ads
Preset voices like Aria or Atlas deliver consistent, high-quality narration without the risk of uncanny valley effects common in early cloning tech. These voices are based on licensed recordings and are optimized for clear, engaging ad copy delivery.
Consistency Benefits
Using the same preset across multiple campaigns ensures brand voice consistency. Freelancers can switch between eight distinct personalities—from warm narrators to energetic promos—without worrying about variations in tone or quality that often plague custom cloned voices.
Technical Integration
The API follows the standard OpenAI speech endpoint shape, allowing you to swap the base_url to https://api.playfomo7.com/v1 and use official OpenAI SDKs directly. This means your existing integration code works with minimal changes, leveraging familiar authentication and request structures.
OpenAI SDK Compatible
Use any official OpenAI SDK by updating the base URL. The request body mirrors the standard speech endpoint, ensuring seamless compatibility with your current development stack without needing a custom client library.
Simple REST API
Send a POST request to /v1/audio/speech with JSON. Specify the model (tts-1 or tts-1-hd), input text, voice, and response_format. The endpoint returns the audio file directly in the response, ready for immediate playback or download in your ad workflow.
- Endpoint:
POST https://api.playfomo7.com/v1/audio/speech - Auth:
Authorization: Bearer tts-... - Formats: mp3, wav, opus, flac, pcm
cURL Example Ready
Start instantly with a single cURL command. Authenticate with your key, select a voice like nova for upbeat promos, and provide your script. The API returns the audio file, allowing you to test integration in minutes without complex setup.
Data Privacy for Ad Content
We understand that ad scripts are your intellectual property. Input text is used strictly to generate the audio file and is never used for training our models or improving the engine for other customers.
No Training on Input
Your campaign copy remains yours. We do not retain your text beyond what is necessary for billing and processing.
No Storage of Audio
Generated audio is returned directly in the response and is not stored on our servers. Only request metadata (time, characters, status) is kept for billing purposes.
Secure Key Management
Each account uses one active API key. You can issue a new key at any time, and the old one stops immediately, ensuring your ad assets stay secure.
Start Generating Radio Spots
Begin your TTS workflow by visiting the /get-api-key/ page and signing in with your Google account. This instant setup grants you a $0.50 trial credit, valid for seven days, allowing you to generate approximately 50,000 characters of ad copy immediately.
Sign Up with Google
Account creation is immediate and requires no credit card. Your balance and usage details are visible on the dashboard from the start.
Get Your API Key
Upon sign-in, you receive a unique Bearer token. This key is active instantly; you can also issue a new one at any time, which immediately invalidates the previous key for security.
- One active key per account
- Instant invalidation of old keys
First Request in Minutes
Use the provided cURL example to send your first text. The API returns an audio file (mp3, wav, etc.) in seconds. For longer scripts, split text into 4096-character chunks to maintain quality and speed.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence.
23 languages
Any voice speaks any of these languages.
