Voice Over Maker API for Professional Video and Radio Spots

By SpotWave editorial team · Updated 2026-11-18

SpotWave API delivers reliable text-to-speech synthesis tailored for ad agencies and content creators producing voice-overs for video and radio spots. This page outlines how to integrate our API into your production workflow, scale bulk synthesis, and maintain consistent brand voice across channels without booking studio time.

You will find specific details on our eight licensed voices, technical integration steps, and transparent pricing. We provide concrete figures on generation speed, character costs, and language support to help you plan your ad campaigns with predictable budgets and high-quality synthetic audio output.

Voice Over Maker API for Professional Video and Radio Spots

Frequently asked questions

What is a voice over maker API?

It is a cloud text-to-speech API where you send text and receive an audio file. The endpoint accepts JSON bodies similar to the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base URL. This enables automated, programmatic generation of voice-overs for video and radio spots without manual recording.

How much does it cost to generate a 30-second radio spot?

Cost depends on character count, not duration. Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. A typical 30-second spot contains roughly 75–90 characters, costing approximately $0.0008 to $0.001. Failed requests are free, ensuring you only pay for successful synthesis outputs.

Can I use the generated audio for commercial advertising?

Yes. The voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. The generated audio files carry an inaudible watermark marking them as synthetic speech, but there are no restrictions on using the output for commercial advertising, video, or radio spots.

Which voices are best for promotional videos?

For promotional content, Felix (energetic, promo) or Nova (bright, upbeat) are suitable choices. Luna (soft, storytelling) works well for narrative ads, while Atlas (neutral, news) suits clear informational spots. Each voice supports all 23 languages, allowing you to match the tone to your specific campaign needs.

How many languages does the API support?

The 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. Any voice can speak any of these languages, and the system guesses the language if not specified.

Do I need to credit the voices in my ads?

The underlying recordings are from LibriVox public-domain audiobooks and LibriTTS-R (CC BY 4.0). While attribution is good practice for CC BY 4.0 content, the API output is a synthetic file marked with an inaudible watermark. Attribution is good practice for CC BY 4.0 content, but there is no mandatory requirement to credit specific voice actors in your final commercial production.

Is there a limit on the length of text per request?

Yes, each request accepts up to 4,096 characters of input text. For longer scripts, you must split the text into parts of this size and join the resulting audio files. This ensures consistent processing and allows for precise control over segment generation during the synthesis workflow.

What happens if the synthesis fails?

If synthesis fails, the charge is returned in full. You are not billed for failed requests. This ensures that you only pay for successfully generated audio files, protecting your budget during bulk synthesis operations or when testing different voice parameters for your advertising campaigns.

Can I control the speed of the voice over?

Yes, you can adjust the speech speed between 0.25 and 4.0. This allows you to speed up dry reads or slow down complex explanations. The speed parameter is part of the JSON request body, enabling precise timing control for your video edits and radio spot durations.

Do you support SSML for intonation control?

No, the API does not support SSML (Speech Synthesis Markup Language). It uses simple text input with optional language codes. If you need intonation control, you must rely on the specific characteristics of the chosen voice preset or adjust the speed parameter within the allowed range.

How long does it take to generate audio?

Typical speed is roughly real time, generating about 25 characters per second of audio. Short phrases may take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue. Longer texts are split and joined, which adds slight processing overhead.

Is there a free trial available?

Yes, signing in with Google provides $0.50 of trial credit, valid for 7 days, covering approximately 50,000 characters. Accounts created with email and password start without trial credit. This allows you to test the API’s quality and workflow before committing to a top-up for commercial production.

What payment methods do you accept?

We accept USDT on the TRON network (TRC-20) only. The minimum top-up is $5, and credits are added automatically within minutes. There are no credit cards, PayPal, subscriptions, or invoices with VAT. Balance does not expire, and there are no monthly plans or minimum spend requirements.

Do you offer voice cloning for brands?

No, we do not offer custom voice cloning. You can choose from eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion) based on licensed recordings. There is no option to upload your own voice or design a custom voice for your specific brand identity.

First request

curl

curl https://api.playcv99.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.mp3

Why choose API voice-overs for ads

Sound wave illustration for: Why choose API voice-overs for ads

Traditional voice-over production requires scheduling studio time and hiring talent, which creates bottlenecks for ad agencies. An API-based solution removes these logistical constraints, allowing you to generate unlimited audio files on demand without coordinating human schedules or studio availability.

This infrastructure supports rapid script revisions. You can produce multiple variations of a single spot in minutes, enabling efficient A/B testing of tone and pacing without incurring the fixed costs of re-recording sessions.

Scale production without studio bookings

Scale production without studio bookings

Eliminate the need for physical studio bookings. Generate high-quality voice-overs in bulk directly from your production pipeline. This approach reduces per-unit costs and accelerates turnaround times for campaign assets.

By removing physical constraints, you can produce dozens of variations simultaneously. This scalability ensures that creative teams are never blocked by resource availability, allowing for faster iteration cycles during the pre-production phase.

  • No studio scheduling conflicts
  • Bulk generation capabilities
  • Reduced per-unit cost

Instant iteration for A/B testing scripts

Test different scripts and voices rapidly. Generate multiple versions of the same ad to determine which performs best with your target audience. This data-driven approach optimizes creative effectiveness before full-scale deployment.

Adjust tone and pacing instantly. If a script needs a slight tweak, regenerate the audio without waiting for a new session. This agility supports agile marketing workflows where creative assets evolve based on real-time performance data.

  • Rapid script variations
  • Data-driven creative optimization
  • Instant tone adjustments

Consistent brand voice across channels

Maintain a uniform audio identity across all your advertising channels. Use the same voice presets for radio spots, YouTube ads, and social media content. This consistency reinforces brand recognition and trust with your audience.

Ensure quality control across all generated audio. Each voice preset delivers a specific, consistent tone. Whether using a warm narrator for storytelling or an energetic voice for promotions, the audio quality remains stable regardless of volume.

  • Uniform audio identity
  • Cross-channel consistency
  • Stable quality control

Licensed voices for advertising

Sound wave illustration for: Licensed voices for advertising

The API provides eight distinct voice presets, all derived from licensed LibriTTS-R recordings (CC BY 4.0) and public-domain audiobook readings. This foundation ensures professional audio quality suitable for commercial use without complex licensing negotiations.

Warm narrator voices for storytelling

Aria and Luna offer soft, clear tones ideal for emotional brand stories. Aria is a warm, clear narrator, while Luna is soft and storytelling.

  • Aria: warm, clear narrator
  • Luna: soft, storytelling

Energetic promo voices for sales

Nova and Felix drive energy in sales copy. Nova is bright and upbeat, while Felix is energetic and promo.

  • Nova: bright, upbeat
  • Felix: energetic, promo

Neutral news voices for clarity

Atlas and Sage ensure clarity in informational spots. Atlas is neutral and news, while Sage is calm and instructional.

  • Atlas: neutral, news
  • Sage: calm, instructional

Technical integration

Sound wave illustration for: Technical integration

Integrate SpotWave into your ad production pipeline with a single endpoint change. Our API mirrors the standard OpenAI speech structure, allowing you to use existing OpenAI SDKs by simply pointing the base URL to https://api.playcv99.com/v1. Send a POST request to /v1/audio/speech with your JSON payload and receive an audio file.

OpenAI-compatible endpoint

Use the standard OpenAI SDKs with zero code refactoring. Change the base_url to https://api.playcv99.com/v1 and use your SpotWave API key (tts-...). The request body accepts model, input, voice, response_format, speed, and language, matching the expected schema exactly.

  • Endpoint: POST https://api.playcv99.com/v1/audio/speech
  • Auth: Authorization: Bearer tts-...
  • SDKs: Official OpenAI libraries work by changing the base URL

Multiple audio formats (MP3, WAV, FLAC)

Select the output format that fits your editing workflow. Choose between MP3, WAV, OPUS, FLAC, or PCM. WAV and FLAC provide lossless quality for broadcast masters, while MP3 is ideal for web delivery. All files include an inaudible synthetic watermark for attribution.

  • MP3, WAV, OPUS, FLAC, PCM

Fast generation speed

Generate voice-overs at roughly real-time speed (25 characters per second). Short phrases take a few seconds; long scripts process sequentially. Under high load, requests may queue but are processed reliably. Split texts over 4,096 characters into multiple requests for efficient bulk synthesis.

Language support

Sound wave illustration for: Language support

Generate voice-overs in 23 languages, from Arabic to Turkish. Any voice can speak any supported language, ensuring consistent audio quality across your international ad campaigns without hiring multiple talent pools.

If the language is not set, it is guessed from the script (Latin text defaults to English). For non-English Latin-script text, we recommend manual override to ensure precise delivery.

Set the language parameter to an ISO code (e.g., de, ja, ko) to override automatic detection. This guarantees the correct pronunciation and accent for specific regional spots, even when the script uses shared characters.

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.

Every voice preset is capable of all 23 languages, allowing you to maintain a uniform audio style across diverse markets.

  • 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 guesses the language from the script's script. Latin text defaults to English.

This simplifies integration for single-language campaigns but may misidentify mixed scripts or non-English Latin text.

Manual language override

Explicitly set the language parameter to your target ISO code. This is critical for non-English Latin-script text to ensure accurate accent and pronunciation.

Note: Vietnamese, Indonesian, Thai, Ukrainian, Romanian, Czech, and Bengali are not supported.

Pricing model

Sound wave illustration for: Pricing model

SpotWave API charges $10 per 1 million characters, equating to $0.01 per 1,000 characters. This transparent model eliminates surprise invoices, allowing ad agencies to forecast production costs precisely for bulk voice-over campaigns. Spaces and punctuation count toward the total, ensuring predictable billing for every script variation.

The pricing structure supports high-volume testing without financial risk. Failed requests are free: if synthesis fails, the charge is returned in full. There are no monthly minimums, seats, or subscriptions, making it ideal for projects with variable weekly output.

Pay per 1,000 characters

Each character in your input text, including spaces and punctuation, contributes to the total count. At $0.01 per 1,000 characters, short phrases incur minimal costs, while long-form radio spots remain affordable. This unit-based billing aligns directly with your creative output, ensuring you only pay for the audio you actually use.

  • $10 per 1 million characters ($0.01 per 1,000 chars)
  • Spaces and punctuation count as characters
  • Predictable costs for bulk synthesis

No monthly minimums

Unlike traditional studio bookings or subscription SaaS platforms, SpotWave requires no minimum spend. You can generate a single 10-second ad spot or ten thousand characters in one billing cycle. Balance does not expire, allowing you to top up only when needed for specific campaign launches.

  • No monthly plans or seats
  • No minimum spend requirements
  • Balance never expires

Free failed requests

If synthesis fails for any reason, the charge is returned in full. This protects your budget during integration testing or when processing edge cases. You can confidently run multiple variations of a script without worrying about penalties for errors or timeouts.

  • Full refund for failed synthesis
  • No penalty for API errors
  • Safe for A/B testing iterations
Pricing model

Data and licensing

Sound wave illustration for: Data and licensing

Our API processes your input text exclusively to generate the audio file. Generated audio is returned in the response and not stored. This ensures your creative assets remain your own without lingering copies in our infrastructure.

We maintain request metadata—such as timestamp, character count, and status—solely for accurate billing and usage tracking. This data is kept minimal and is not repurposed for training our models or improving the voice engine, preserving the integrity of your specific ad campaigns.

Text not used for training

Unlike many consumer-grade TTS services, we do not use your input text or generated audio to train our base models. Your ad scripts and voice outputs remain distinct from the dataset used to improve the underlying voice engine, ensuring your brand’s unique content doesn’t influence future generic generations.

Licensed base recordings

All eight voices in our library are derived from licensed recordings. The base audio data comes from LibriTTS-R, which is licensed under CC BY 4.0. Additionally, many source readings originate from LibriVox public-domain audiobook recordings. This foundation provides high-quality, natural-sounding speech suitable for commercial advertising without complex royalty chains for each generated clip.

  • Base data: LibriTTS-R (CC BY 4.0)
  • Source material: LibriVox public-domain readings
  • Clear licensing for ad agencies

Synthetic watermark included

Every audio file generated by our API includes an inaudible digital watermark. This marker identifies the file as synthetic speech produced by our engine. It serves as a transparent indicator of AI-generated content, which is increasingly important for broadcast compliance and platform-specific advertising standards.

Performance metrics

Sound wave illustration for: Performance metrics

Generation speed typically mirrors real-time, processing roughly 25 characters of text per second for longer scripts. Short phrases may take a few seconds to synthesize. For bulk production, split texts into parts of up to 4096 characters and join the resulting audio files to maintain efficiency.

Real-time generation speed

Expect synthesis times that align with the audio duration, averaging about 25 characters per second for standard-length texts. Short phrases might require a few additional seconds for processing. This predictable latency allows you to estimate production times accurately for high-volume ad campaigns.

Queue management under load

Requests are processed sequentially. Under heavy load, a request may wait in a queue before synthesis begins. This linear processing ensures consistent quality and prevents resource contention, though it may introduce slight delays during peak usage periods.

Reliable API status

The API maintains a stable connection without guaranteed uptime SLAs. Standard monitoring covers basic availability. Failed requests incur no charge, providing a safety net for budget predictability during integration testing or high-volume bursts.

Common use cases

Sound wave illustration for: Common use cases

SpotWave API enables rapid content production cycles for advertising teams. By synthesizing voice-overs programmatically, teams can generate multiple script variations for A/B testing without booking studio time or coordinating actor schedules.

YouTube ad spots

Generate short, engaging voice-overs for digital video ads. Use energetic voices like Felix for promos or Aria for narrative storytelling. Scripts under 4096 characters are processed quickly, allowing for high-volume content creation tailored to specific platforms.

  • Supports 23 languages for global campaigns
  • Fast generation speed for quick iterations

Radio broadcast segments

Produce clear, broadcast-ready audio files in WAV or FLAC formats. Neutral voices like Atlas ensure news-style clarity, while Sage provides calm instructional tones. Ideal for creating consistent brand voice across multiple radio spots.

  • High-quality output formats for professional use
  • Consistent tone across all generated segments

E-commerce product videos

Create compelling product descriptions and reviews programmatically. Use friendly voices like Milo for conversational tones or Luna for soft storytelling. Each request is billed per character, ensuring predictable costs for bulk synthesis.

  • Predictable pricing based on character count
  • Support for multiple languages and dialects

Get started

Sound wave illustration for: Get started

Create your account on the /get-api-key/ page using Google or email. Google sign-ups include $0.50 trial credit valid for seven days, while email accounts start with zero balance.

Generate your API key and top up via USDT on the TRON network to begin bulk synthesis immediately.

Sign up for trial credit

Visit /get-api-key/ and choose Google or email registration. Google authentication grants $0.50 credit (50,000 characters) valid for 7 days. Email accounts start without trial credit.

Generate your API key

Your dashboard displays a single active Bearer token. You can issue a new key at any time; the old one stops immediately. Use this key with the OpenAI SDK or plain HTTP.

Test with a curl command

Send a POST request to https://api.playcv99.com/v1/audio/speech. Replace YOUR_KEY and your text payload to receive an audio file in MP3, WAV, or other formats.

  • Endpoint: POST https://api.playcv99.com/v1/audio/speech
  • Auth: Authorization: Bearer YOUR_KEY
  • Body: {"model": "tts-1", "voice": "nova", "input": "Hello world", "response_format": "mp3"}

Listen to the 8 voices

Each sample below was generated by this API from the same sentence.

Avatar of the voice aria
ariafemale
Avatar of the voice nova
novafemale
Avatar of the voice luna
lunafemale
Avatar of the voice sage
sagefemale
Avatar of the voice felix
felixmale
Avatar of the voice milo
milomale
Avatar of the voice atlas
atlasmale
Avatar of the voice orion
orionmale

23 languages

Any voice speaks any of these languages.

Sources and further reading

  1. Wikipedia
  2. Creative Commons Attribution 4.0
  3. openai-node on GitHub
  4. Node.js documentation
  5. LibriTTS-R corpus (OpenSLR 141)
  6. TRON developer hub: TRC-20
  7. LibriTTS-R paper (arXiv 2305.18802)
  8. Python documentation
  9. LibriVox public-domain audiobooks
  10. OpenAI API reference: create speech
  11. ISO 639 language codes
  12. FFmpeg documentation

More on this site