Frequently asked questions
What is the character limit per request?
Each API request accepts up to 4096 characters of input text. For longer scripts, split the text into chunks of this size and join the resulting audio files. Spaces and punctuation count toward the character limit, so plan your payload accordingly to stay within the single-request boundary.
Which voices are best for TikTok ads?
All eight presets are suitable for TikTok ads. Use Felix for energetic promos, Nova for bright tones, or Luna for soft storytelling. Atlas works for neutral spots, while Orion suits deep content. Sage is ideal for instructional clips, and Aria and Milo also deliver clear audio. Any voice can speak any supported language, ensuring versatile options for short-form video content without subjective ranking.
How many languages does the API support?
The API supports 23 languages, including English, Spanish, German, French, Japanese, Korean, Chinese, Arabic, Hindi, and Portuguese. Any voice can speak any of these languages. If the language is not specified, the system guesses it from the script, defaulting to English for Latin script.
Can I control the speed of the voice?
Yes, you can adjust the speed parameter between 0.25 and 4.0. This allows you to speed up or slow down the voice output to match your video pacing. The speed adjustment applies to the generated audio file directly, ensuring seamless integration with your editing workflow.
Is the audio file MP3 or WAV by default?
The API does not have a single default format; you specify the format in the request. Supported formats include mp3, wav, opus, flac, and pcm. Choose the format that best fits your production pipeline.
Does the API support SSML formatting?
No, the API does not support SSML formatting. It accepts plain text input. You control pacing and tone primarily through the voice selection and speed parameters. For precise control, split your text into separate requests for each phrase or sentence to manage timing manually.
How are failed requests billed?
Failed requests are free. If synthesis fails, the charge is returned in full. You are only billed for successful audio generation. This ensures you pay only for usable output, protecting your budget from errors or temporary processing issues during high-load periods.
Is there a free trial for new accounts?
Yes, signing in with Google provides a $0.50 trial credit, valid for 7 days. This allows about 50,000 characters of generation. Accounts created with email and password start without trial credit.
What payment methods are accepted?
We accept USDT on the TRON network (TRC-20) only. There are no credit cards, PayPal, or subscriptions. Minimum top-up is $5. Credits are added automatically within minutes of transfer. Balance does not expire, and there are no monthly plans or minimum spend requirements.
Can I clone my own voice?
No, we do not offer custom voice cloning. You must choose from the eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). These are based on licensed recordings from LibriTTS-R, from LibriVox public-domain audiobook readings. Each generated file includes an inaudible watermark marking it as synthetic speech.
Are the voices real people or synthetic?
The voices are based on licensed recordings: LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. They are based on LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. While the source material is human, the output is generated by our TTS engine and carries an inaudible watermark indicating synthetic origin.
Is there an SLA for uptime?
No, there is no SLA or uptime guarantee. We do not offer enterprise contracts or on-premise installations. Support is via email only. Requests are processed sequentially, so under load, generation may wait in a queue. We recommend building retry logic into your integration for reliability.
Do I need a developer to use this?
A developer is recommended to integrate the API into your workflow. You can use the official OpenAI SDKs by changing the base URL or use plain HTTP. The API requires constructing JSON bodies with specific fields like model, input, voice, and response format. Basic programming knowledge is needed.
How long does generation take?
Generation is roughly real-time on long texts, processing about 25 characters per second. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is efficient for batch processing of advertising scripts.
First request
curl
curl https://api.rn98.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.mp3Programmatic Voice Generation
SpotVoce provides a standardized TTS API designed for automated production pipelines. Send text via a simple POST request and receive synthesized audio files immediately. The endpoint accepts JSON bodies identical to the OpenAI speech format, allowing agencies to integrate voice generation directly into existing creative workflows without manual hand-offs.
Standardized API Endpoint
Interact with the API using standard HTTP requests. The endpoint POST /v1/audio/speech accepts JSON payloads containing the model, input text, voice preset, and desired output format. This structure ensures compatibility with common programming libraries and simplifies integration into backend systems used by production teams.
- POST https://api.rn98.info/v1/audio/speech
- JSON request body
- Compatible with OpenAI SDKs
Instant Audio Delivery
Text is converted to audio files with minimal latency. Short phrases are generated in seconds, while longer texts process at roughly real-time speed. The API returns the audio file directly in the response, enabling immediate playback or download within your application.
Automated Workflow Integration
Integrate voice generation into your ad production stack. Scripts can automatically split long texts into 4096-character chunks, synthesize each part, and join the audio files. This programmatic approach eliminates manual recording steps and ensures consistent voice quality across all generated spots.
Voice Presets for Advertising
SpotVoce provides eight distinct voice presets engineered for advertising and radio production workflows. Each voice is derived from licensed recordings, ensuring consistent tonal quality across high-volume campaigns without manual voice actor coordination.
Narrative and Storytelling
Aria, Luna, and Nova offer warm, clear, and upbeat tones ideal for brand storytelling. Aria serves as a warm, clear narrator, Luna delivers soft storytelling, and Nova provides bright energy.
- Aria: Warm, clear narrator
- Luna: Soft, storytelling tone
- Nova: Bright, upbeat delivery
Energetic Promo Voices
Felix and Milo are optimized for high-energy commercial content. Felix delivers an energetic, promo-ready voice, while Milo offers a friendly, conversational tone suitable for direct-to-consumer ads. Both voices sustain engagement in short-form video and radio spots.
- Felix: Energetic, promo style
- Milo: Friendly, conversational
Neutral News and Instructional
Atlas, Sage, and Orion provide authoritative and clear delivery for informational content. Atlas offers a neutral news tone, Sage delivers calm instructional clarity, and Orion provides a deep, documentary-style voice. These presets ensure professional neutrality for corporate and educational audio.
- Atlas: Neutral, news style
- Sage: Calm, instructional
- Orion: Deep, documentary
Multi-Language Support
SpotVoce supports 23 languages, enabling production teams to localize ad spots and radio drafts without managing separate voice contracts. Any preset voice can deliver any supported language, ensuring consistent brand tone across markets.
The API automatically detects language from the input script, defaulting to English for Latin text. For non-English Latin-script content, explicit tagging guarantees accurate pronunciation and prosody.
23 Supported Languages
We support Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Voices are not language-locked; any preset can speak any supported language.
- 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 the language field is omitted, the system infers the language from the script. Latin-script text defaults to English. This simplifies integration for primary English campaigns.
Explicit Language Tagging
For non-English Latin-script text, set the language parameter to the ISO code. This prevents misidentification and ensures correct accent and rhythm in the generated audio.
Technical Specifications
The API accepts text inputs up to 4096 characters per request. For longer scripts, split the text into parts and join the resulting audio files. Spaces and punctuation count toward the character limit.
Character Limits per Request
Each request supports a maximum of 4096 characters. Text exceeding this limit must be segmented by the client application before synthesis begins.
- Maximum input: 4096 characters
- Includes spaces and punctuation
- Split and join for longer texts
Audio Format Options
Output formats include mp3, wav, opus, flac, and pcm. Select the format that best fits your post-production pipeline or delivery requirements.
- mp3, wav, opus, flac, pcm
Speed Control Parameters
Adjust playback speed between 0.25 and 4.0. This allows precise timing adjustments to match visual cues in video spots without re-recording.
- Range: 0.25–4.0
- Fine-grained control
Pricing Model
SpotVoce charges $0.01 per 1,000 characters, including spaces and punctuation. This linear model ensures predictable costs for high-volume ad production without hidden fees for longer scripts or multiple voice variations.
Per-Character Billing
Each request is billed based on the input character count. Failed synthesis requests incur no charge, and credits are returned in full if processing fails.
- $0.01 per 1,000 characters
- Spaces and punctuation count as characters
- Failed requests are free
No Monthly Subscriptions
There are no recurring monthly plans, seat licenses, or minimum spend requirements. You only pay for the audio you generate, making it easy to scale costs directly with campaign volume.
Pay-As-You-Go Structure
Top-ups are processed via USDT (TRC-20) on the TRON network with a $5 minimum. Balances do not expire, allowing you to fund accounts once for long-term production needs.
- Minimum top-up: $5
- Payment: USDT on TRON network
- Balance never expires

Use Cases for Agencies
SpotVoce enables agencies to generate voice-overs programmatically, eliminating manual hand-offs between voice talent and editors. By sending text via a standard API, production teams receive audio files directly into their workflow, ensuring consistent branding across campaigns.
This approach allows creative teams to iterate rapidly on tone and pacing.
Social Media Ad Spots
Generate varied voice options for A/B testing video ads across platforms like TikTok and Instagram. Use energetic presets like Felix for promos or Luna for storytelling to match brand voice quickly.
Scale content production by generating localized versions of campaigns in multiple languages without hiring new voice actors for each region.
- Rapid A/B testing of voice tones
- Multi-language scaling without new hires
Radio Spot Drafts
Create quick audio drafts for radio spots using presets like Atlas for neutral news or Orion for deep documentary styles. Validate script pacing and timing before committing to studio recordings.
Use the API to produce placeholder audio for client pitches, demonstrating the final tone without incurring full production costs.
- Fast script validation
- Low-cost client pitch assets
E-Learning Voice Overs
Produce clear, instructional audio for e-learning modules using Sage or Nova. Split long texts into 4096-character chunks to maintain audio quality and manage processing queues effectively.
Ensure consistent voice profiles across course modules by reusing the same voice preset for all generated audio files.
- Consistent module voices
- Chunked processing for long texts
Quality and Consistency
Consistency is critical when scaling voice-over production across multiple campaigns. Each voice preset maintains a uniform tone and delivery style, ensuring your brand audio remains recognizable regardless of volume or length. This standardization eliminates the variability often found in human casting or inconsistent AI outputs.
Every generated audio file contains an inaudible synthetic watermark, clearly marking the content as AI-generated. This provides a reliable audit trail for compliance and rights management without affecting the listener's experience.
Consistent Voice Profiles
Our eight presets, from the warm narrator 'Aria' to the energetic promo voice 'Felix', are derived from licensed recordings. They deliver predictable, repeatable results ideal for ad spots and radio drafts where tonal consistency matters more than unique performance nuances.
Synthetic Watermarking
Each audio file carries a unique, inaudible watermark identifying it as synthetic speech. This allows for easy verification of content origin without requiring additional metadata or separate tracking systems.
No Training Data Usage
Your input text is used solely to generate the audio response. We do not use your input data or generated audio to train our models, ensuring your creative assets remain distinct and private.
Integration Guide
Integrate SpotVoce into your production pipeline using the official OpenAI SDKs by simply overriding the base URL. This approach allows your existing code to generate audio files via the standard POST /v1/audio/speech endpoint without rewriting client libraries.
OpenAI SDK Compatibility
The API mimics the OpenAI speech endpoint structure, enabling immediate compatibility with standard OpenAI SDKs for Python, Node.js, and other languages. You can reuse existing authentication and retry logic with minimal configuration changes.
- Compatible with official OpenAI SDKs
- Standard request/response JSON schema
- Supports Python, Node.js, and HTTP clients
Base URL Configuration
Configure your SDK client to point to the SpotVoce API base URL: https://api.rn98.info/v1. This single change directs all requests to our inference engine while maintaining the familiar endpoint paths.
- Base URL: https://api.rn98.info/v1
- Endpoint: /v1/audio/speech
- No additional path prefixes required
Authentication Headers
Include your unique API key in the Authorization header for every request. Use the format Bearer tts-... where the token is issued from your account dashboard. Keys are single-active and revoke immediately upon reissuance.
Support and Limits
Rate limits are set at 60 requests per minute per key, with a lower 10 requests per minute threshold for new accounts before the first top-up. Requests are processed sequentially, so high volume may result in queue delays.
Rate Limiting Structure
Each API key is capped at 60 requests per minute. New accounts start with a 10 requests per minute limit until a top-up is processed. Long texts are split into 4096-character chunks, each counting as a separate request.
Error Handling
Failed synthesis requests are processed instantly and refunded in full, ensuring no character credit is lost during errors. The API returns standard HTTP status codes to indicate success or failure, allowing your integration to retry or log the event.
Email Support Channel
Support is available exclusively via email. There is no phone number or live chat option. We respond to technical and billing inquiries via email.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Her gentle tone reduces listener fatigue during longer audio spots.
23 languages
Any voice speaks any of these languages.
