Siri Voiceover Generator API for Short-Form Video

By ShortForm AI editorial team · Updated 2026-11-18

This page provides the technical documentation and integration guide for ShortForm AI, the TTS API built for creators making TikTok, Reels, and Shorts. You will find the exact endpoint structure, voice presets like Aria and Felix, and code examples to generate voiceovers programmatically without manual recording.

We focus on reliable, on-demand audio generation for no-code and lightweight engineering workflows. Use our API to automate voiceover creation, control speed, and select from 23 languages. Everything is defined by concrete numbers and clear integration steps, so you can ship content faster.

Siri Voiceover Generator API for Short-Form Video

Frequently asked questions

What is a Siri voiceover generator API?

Q: What is a text-to-speech API? A: It is a cloud text-to-speech API. You send text via a POST request to https://api.play78j.com/v1/audio/speech and receive an audio file. It uses the same request shape as the OpenAI speech endpoint, allowing you to use official OpenAI SDKs by changing the base URL to our API domain.

Which voices are best for TikTok videos?

Nova is bright and upbeat, ideal for energetic content. Felix is energetic and suited for promos. Luna offers soft storytelling, while Milo provides a friendly, conversational tone. Atlas is neutral for news-style clips, and Orion delivers a deep, documentary voice. All eight presets support all 23 languages.

How much does the API cost per video?

Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with the charge returned in full. There are no monthly plans, seats, or minimum spend requirements, so you only pay for what you generate.

Can I generate voiceovers in multiple languages?

Yes, the API supports 23 languages including English, Spanish, German, French, Japanese, and Korean. Any voice can speak any supported language. If the language field is omitted, the system guesses the language from the script, defaulting to English for Latin text.

Does the API support speed adjustment?

Yes, you can adjust the speed between 0.25 and 4.0. This allows you to speed up narration for quick shorts or slow it down for emphasis. The speed parameter is included in the JSON body of your POST request to the speech endpoint.

What happens if a 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. You can retry the request with the same text and parameters without incurring additional costs.

Is there a limit on video length?

The API limits input text to 4096 characters per request. For longer texts, split them into parts of up to 4096 characters and join the resulting audio files. There is no direct video length limit, as the API generates audio files, not video files.

How do I integrate this with CapCut?

Generate the audio file via the API using your preferred HTTP client or OpenAI SDK. Download the resulting audio file (mp3, wav, opus, flac, or pcm). Upload the audio file to CapCut as a voiceover track. The API does not provide a direct CapCut plugin or SDK.

Do I need to record my own voice?

No, you do not need to record your own voice. The API generates synthetic speech from text using licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. Each generated file carries an inaudible watermark marking it as synthetic speech, but no human recording is required for creation.

What audio formats are supported?

The API supports mp3, wav, opus, flac, and pcm formats. Specify the desired format in the response_format field of your request. These formats cover most video editing needs, including high-quality lossless options and compressed formats suitable for social media uploads.

Can I use the audio commercially?

The voices are based on licensed recordings (LibriTTS-R CC BY 4.0, LibriVox public domain). The voices are based on licensed recordings (LibriTTS-R CC BY 4.0, LibriVox public domain). Generated audio is returned in the response and not stored by the service. You retain the generated file for your use.

How long does generation take?

Generation is roughly real time, about 25 characters per second. Short phrases take a few seconds. Requests are processed sequentially, so under load, a request may wait in a queue.

Is there a free trial available?

Yes, signing in with Google gives $0.50 of credit, valid for 7 days, covering about 50,000 characters. Accounts created with email and password start without trial credit. The balance does not expire, and you can top up with USDT on the TRON network.

What payment methods are accepted?

We accept USDT on the TRON network (TRC-20) only. The minimum top-up is $5. Credits are added automatically within minutes after the transfer. We do not accept credit cards, PayPal, or subscriptions. There are no invoices with VAT or monthly plans.

First request

curl

curl https://api.play78j.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

How it works

Sound wave illustration for: How it works

The ShortForm AI API converts text into synthetic voiceovers programmatically. You send a JSON payload to the speech endpoint with your text, voice selection, and language preference. The system processes the request using standard TTS-1 engines, ensuring consistent audio quality without manual recording.

Send text via API

Send text via API

Use the POST endpoint to submit your script. Each request accepts up to 4,096 characters of input text. For longer scripts, split the content into parts and generate audio for each segment separately before joining them.

  • Supports multiple languages including English, Spanish, and Arabic

Receive audio file

Receive the generated audio file directly in your response. You can choose formats like MP3, WAV, or OPUS. Failed requests incur no charge, ensuring you only pay for successful generations.

  • MP3, WAV, OPUS, FLAC, and PCM formats

Integrate with video tools

Download the audio file and import it into your editing workflow. The API allows speed adjustments from 0.25x to 4.0x to match video pacing. This automation eliminates manual recording for TikTok, Reels, and Shorts.

Voices for your content

Sound wave illustration for: Voices for your content

Short-form video relies on immediate engagement. Our API provides distinct vocal presets designed to match the pacing of TikTok, Reels, and Shorts without manual recording.

Female voices: Aria, Nova

Aria offers a warm, clear narrator tone ideal for storytelling or educational content. Nova delivers a bright, upbeat delivery suitable for energetic promotional clips or quick tips.

Male voices: Felix, Milo

Felix is energetic and perfect for promo content or high-energy reviews. Milo provides a friendly, conversational style that works well for direct-to-camera style scripts or casual commentary.

Neutral and deep options

Atlas provides a neutral, news-style delivery for clear information delivery. Orion offers a deep, documentary tone suitable for serious or atmospheric content. Any voice can speak any of the 23 supported languages.

Supported languages

Sound wave illustration for: Supported languages

Our API supports 23 languages, allowing you to localize content for global audiences without hiring voice actors. Every voice preset can speak any supported language, ensuring consistent audio quality across all regions.

The system automatically detects the language from the text script if you do not specify it. For non-English Latin-script text, we recommend explicitly setting the language field to avoid defaulting to English.

English, Spanish, French

These are the most commonly requested languages for short-form video content. English defaults if no language is specified for Latin-script text. Spanish and French voices deliver clear, natural narration suitable for tutorials and storytelling.

  • Full support across all 8 voice presets
  • Automatic detection for Latin scripts
  • Ideal for global reach

German, Japanese, Korean

Support extends to high-demand markets with distinct linguistic structures. The synthetic speech carries an inaudible watermark that marks it as synthetic speech. This is critical for maintaining viewer engagement in these regions.

  • Accurate phoneme handling
  • Natural intonation patterns
  • Supports diverse voice tones

Arabic, Hindi, Portuguese

We cover major global languages including Arabic, Hindi, and Portuguese. Each voice preset adapts to the specific nuances of these languages. This allows creators to produce localized content efficiently using the same API endpoint.

  • Broad global coverage
  • Consistent voice quality
  • Efficient localization workflow

Technical specifications

Sound wave illustration for: Technical specifications

The API uses the standard OpenAI-compatible endpoint at https://api.play78j.com/v1/audio/speech. This allows you to use the official OpenAI SDKs by simply changing the base URL, ensuring immediate compatibility with existing codebases.

OpenAI-compatible endpoint

Send a POST request with JSON body containing model, input, voice, and response_format. Authentication is handled via Authorization: Bearer tts-... header. The request shape mirrors the OpenAI speech endpoint exactly.

  • Endpoint: POST https://api.play78j.com/v1/audio/speech
  • Auth: Bearer token required
  • Max input: 4096 characters

Multiple audio formats

Specify response_format as mp3, wav, opus, flac, or pcm. MP3 is optimal for web playback, while WAV or FLAC provide lossless quality for editing in post-production.

Speed control 0.25–4.0x

Adjust the speed parameter between 0.25 and 4.0 to match your video pacing. Faster speeds compress voiceovers for quick cuts; slower speeds enhance clarity for instructional content.

Pricing model

Sound wave illustration for: Pricing model

Cost is calculated strictly by character count, including spaces and punctuation. You pay $10 per million characters generated, equating to $0.01 per 1,000 characters. This transparent model ensures you only spend on actual usage without hidden fees or monthly subscriptions.

$10 per million characters

The API charges $10 for every one million characters processed. This rate applies to all models, including tts-1 and tts-1-hd, which use the same engine and price. Short phrases cost cents; long scripts scale linearly. There are no minimum spend requirements or tiered pricing levels.

  • $0.01 per 1,000 characters
  • Spaces and punctuation count as characters
  • No minimum spend or monthly plans

Pay-as-you-go balance

Fund your account with USDT on the TRON network (TRC-20). Top-ups start at $5 and credit automatically within minutes. Your balance never expires, and you can generate voiceovers whenever needed without waiting for invoice cycles or subscription renewals.

  • USDT (TRC-20) only
  • Minimum top-up: $5
  • Credits in minutes, no expiry

Free failed requests

If a synthesis request fails due to server errors or invalid parameters, you are not charged. The full cost is returned to your balance. You only pay for successfully generated audio files, ensuring you never lose credit for broken outputs.

Pricing model

Integration examples

Sound wave illustration for: Integration examples

Generate voiceovers programmatically for TikTok, Reels, and Shorts. Use standard HTTP requests or Python libraries to send text and receive audio files instantly.

Integrate directly into your video editing pipeline or automation tools. No manual recording required; just send text and get MP3 or WAV output.

Python script example

Use the requests library to POST your text to the endpoint. Replace YOUR_API_KEY with your key from the dashboard.

Send the payload with model, input, and voice parameters. The response contains the binary audio data ready for saving.

cURL command example

Execute a single command to generate speech. Replace YOUR_API_KEY and YOUR_VOICE with your specific credentials.

This approach is ideal for quick testing or shell-based automation workflows in your CI/CD pipeline.

OpenAI SDK configuration

Use the official OpenAI Python SDK by pointing base_url to https://api.play78j.com/v1.

Pass your tts-... key as the API key. The request shape is identical to the OpenAI Speech endpoint, ensuring easy migration.

Why use an API

Sound wave illustration for: Why use an API

Short-form video creators generate high volumes of content, requiring a scalable voiceover solution that keeps pace with daily posting schedules. An API eliminates the bottleneck of manual recording sessions, allowing you to generate hours of audio in minutes rather than hours.

By integrating voice synthesis directly into your content pipeline, you maintain consistent audio quality across all videos. This consistency builds audience recognition while removing the variability of human recording environments, ensuring every clip sounds professional without the need for studio equipment.

Automate bulk generation

Process multiple scripts simultaneously by splitting long texts into 4096-character chunks and joining the audio files. This allows you to queue dozens of voiceovers for a week’s worth of shorts in a single API call sequence, fitting seamlessly into your existing workflow.

  • Requests are processed one after another, so under load a request may wait in a queue.
  • Automate script-to-audio conversion without human intervention
  • Handle varying text lengths with automatic chunking

Consistent audio quality

Every generated file uses the same engine and voice presets, ensuring tonal consistency across your TikTok, Reels, or Shorts channel. Unlike human recordings, there is no fatigue, background noise, or volume fluctuation to correct in post-production.

  • Uniform tone across all generated clips
  • No background noise or mic artifacts
  • Standardized output formats (mp3, wav, opus)

No manual recording needed

Eliminate the need for microphones, pop filters, and recording booths. You can generate voiceovers from any device with internet access, allowing your team to focus on scripting and editing rather than audio engineering.

  • No hardware dependencies
  • Generate audio from anywhere
  • Reduce setup time to zero

Data privacy

Sound wave illustration for: Data privacy

We process your input text strictly to generate the audio response. The source text is not used for training our models or improving the TTS engine, ensuring your scripts remain yours.

Text not used for training

Your input text is used only to produce the audio and is not used for training.

Audio not stored after delivery

Generated audio is returned in the response and not stored.

Metadata kept for billing

Request metadata (time, characters, status) is kept for billing.

Get started

Sound wave illustration for: Get started

Create your account via the /get-api-key/ page using Google or email. You receive $0.50 in trial credit immediately, valid for 7 days, allowing you to test the API without payment details.

Once signed in, your dashboard displays your active API key and current balance. You can issue a new key at any time, instantly invalidating the previous one.

Sign up for free trial

Visit the sign-up page and authenticate with Google or email/password. Accounts receive $0.50 credit (~50,000 characters) instantly. This trial expires after 7 days.

Generate API key

Your account dashboard lists your unique API key starting with 'tts-'. You can generate a new key at any moment; the old one stops immediately. Use this key in the Authorization header.

Make your first request

Send a POST request to https://api.play78j.com/v1/audio/speech with your text and voice selection. Receive the audio file directly in the response. Failed requests are free.

Use the provided curl example or OpenAI SDK to start generating voiceovers for your short-form videos immediately.

  • Endpoint: POST /v1/audio/speech
  • Auth: Bearer tts-<your-key>
  • Format: JSON body

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Matching voice personas to your target demographic helps align audio tone with viewer expectations.

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. IETF RFC 7845: Ogg Opus
  3. Creative Commons Attribution 4.0
  4. Python documentation
  5. W3C WAI: making audio and video accessible
  6. OpenAI API reference: create speech
  7. TRON developer hub: TRC-20
  8. ISO 639 language codes
  9. openai-node on GitHub
  10. LibriTTS-R paper (arXiv 2305.18802)
  11. Tether (USDT)
  12. Node.js documentation

More on this site