Transform Your Video Dubbing Workflow with Our Cloud TTS API

By VoxLocale editorial team · Updated 2026-11-18

VoxLocale provides a reliable text-to-speech API designed specifically for localization and dubbing agencies. Automate your voice-over production with consistent voices across 23 languages and 8 distinct presets. Scale your video dubbing pipeline without hiring extra talent or managing complex infrastructure.

Our platform handles the heavy lifting of audio generation, letting you focus on creative direction. Whether you need warm narrators for documentaries or energetic voices for promos, our API delivers high-quality synthetic speech. Get started quickly with a simple API key and integrate directly into your existing workflow.

Transform Your Video Dubbing Workflow with Our Cloud TTS API

Frequently asked questions

What is a narrator online API?

A narrator online API is a cloud service that converts text into audio files via HTTP requests. You send text to POST /v1/audio/speech and receive synthesized speech. It automates voice-over production for dubbing agencies, allowing you to generate audio programmatically without hiring human narrators for every project.

How does TTS compare to human voice-over for dubbing?

TTS offers consistent quality across 23 languages and 8 voices without scheduling constraints. Our API generates audio at roughly real-time speed (25 characters per second) for long texts. It scales effortlessly for high-volume dubbing pipelines, though it lacks the subjective artistic variation of human performance.

Which voices are best for documentary dubbing?

Orion is ideal for documentaries, described as deep and documentary-style. Atlas provides a neutral, news-like tone suitable for factual content. For softer storytelling, Luna offers a soft, storytelling voice. These presets ensure consistent branding across your localized video content without the variability of different human voice actors.

Can the API handle multiple languages in one script?

Yes, you can mix languages within a single request up to 4096 characters. The API supports 23 languages, and any voice can speak any supported language. You can optionally set the 'language' field to guide the engine, or let it guess based on the script's script (e.g., Latin defaults to English).

How accurate is the auto-language detection?

The API guesses the language from the script if not specified. Latin script text defaults to English. For non-English Latin-script text, we recommend explicitly setting the 'language' parameter for accuracy. It supports 23 languages including Arabic, Chinese, Japanese, and Swahili, covering most major dubbing markets.

Is the API suitable for commercial use?

Yes, the API is designed for commercial workflows. Generated audio carries an inaudible watermark marking it as synthetic speech. Input text is not used for training, and generated audio is not stored. You pay only for what you use, making it cost-effective for agency-scale commercial dubbing projects.

Do I need to split long scripts manually?

The API accepts up to 4096 characters per request. For longer scripts, you must split the text into parts of up to 4096 characters and join the resulting audio files. This allows you to handle long documentaries or series by chunking the input text before sending it to the endpoint.

What formats do you support for video editing?

We support mp3, wav, opus, flac, and pcm via the 'response_format' field. These formats cover most video editing needs. You can choose the best balance between file size and quality for your post-production pipeline, ensuring compatibility with standard video editing software and workflows.

Are the voices royalty-free?

Voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and LibriVox public-domain audiobook readings. While the source material is public domain or CC BY 4.0, each generated file carries an inaudible watermark marking it as synthetic speech. This ensures clear provenance for your commercial dubbing projects.

How does the character limit work?

You are charged $0.01 per 1,000 characters, including spaces and punctuation. Each API request handles up to 4096 characters. Failed requests are free. Your balance deducts based on the total character count processed, allowing precise cost control for your agency's dubbing volume without monthly subscription fees.

Can I change the voice mid-script?

Yes, by splitting your script into multiple requests. Since each request generates a separate audio file, you can assign different voices to different chunks. Simply concatenate the resulting audio files to create a final track with varied voice personalities, ideal for multi-character dialogue or section changes.

Is there a limit on characters per month?

No, there is no monthly character limit or minimum spend. You pay per character used ($10 per million characters). Balance does not expire. You can use as much or as little as needed, making it ideal for agencies with fluctuating dubbing volumes and project-based workflows.

How do I troubleshoot a failed request?

Failed requests are free, with the charge returned in full. Check your input text length (max 4096 characters) and voice validity. Ensure your API key is active. If issues persist, contact support via email. We do not offer live chat or phone support, so email is the primary channel.

Do you offer volume discounts for agencies?

No, we do not offer volume discounts or enterprise contracts. The price is flat at $10 per million characters for all users. There are no monthly plans, seats, or minimum spends. This simplicity allows agencies to scale costs directly with usage without negotiating custom pricing tiers.

First request

curl

curl https://api.playyy9.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

Automate Your Dubbing Pipeline

Sound wave illustration for: Automate Your Dubbing Pipeline

VoxLocale’s TTS API lets localization agencies replace manual voice-over casting with a reliable, character-based generation pipeline. By sending text via a standard JSON request, you receive synchronized audio files ready for dubbing, ensuring consistent audio quality across all target languages without managing multiple talent contracts.

Our platform handles 23 languages and 8 distinct voice presets, allowing you to scale your video dubbing production. Generate audio for entire scripts by splitting texts into 4096-character chunks, then join the resulting files seamlessly. This eliminates the logistical bottleneck of scheduling voice actors and reduces per-project overhead significantly.

Consistent Voice Across Languages

Consistent Voice Across Languages

Maintain brand identity by assigning specific voices like Aria or Felix to your key characters, regardless of the target language. Our engine supports 23 languages, including Arabic, Chinese, Spanish, and Japanese, with auto-detection for Latin scripts. You can explicitly set the language ISO code to ensure accurate pronunciation and tone for non-English texts.

  • 8 distinct voice presets (e.g., Luna for storytelling, Atlas for news)
  • Support for 23 languages including European, Asian, and Latin American markets
  • Explicit language setting overrides auto-detection for precise control

Instant Audio Generation

Receive audio files directly in your API response in formats like MP3, WAV, or OPUS. The API processes requests sequentially, so generation is roughly real-time on long texts. For longer texts, split the input into parts under 4096 characters, generate each chunk, and concatenate the results for a complete track.

  • Standard JSON request body compatible with OpenAI SDKs
  • Support for MP3, WAV, OPUS, FLAC, and PCM formats
  • Speed control from 0.25x to 4.0x for timing adjustments

Scale Without Hiring Talent

Eliminate the need to hire, book, or manage voice actors for every new project. With VoxLocale, you can generate audio assets. Your balance does not expire, and you only pay for successful characters ($0.01 per 1,000 characters), making it cost-effective for high-volume localization workflows.

  • No monthly fees or minimum spend requirements
  • Pay only for successful synthesis; failed requests are free
  • Unlimited character generation based on your credit balance

Voices That Fit Every Script

Sound wave illustration for: Voices That Fit Every Script

Select from eight distinct voice presets designed to match your content’s tone. Our engine lets you choose the perfect vocal identity for each project, ensuring consistency across your entire dubbing pipeline without the need for additional talent.

Warm Narrators for Documentaries

For long-form content, choose from warm, clear narrators like Aria or soft, storytelling voices like Luna. These presets are suitable for documentary scripts.

  • Aria: Warm, clear narrator
  • Luna: Soft, storytelling voice

Energetic Promos and Ads

Drive engagement with high-energy voices. Felix offers an energetic tone perfect for promotional content, while Nova provides a bright, upbeat delivery. These voices are suitable for short, punchy scripts.

  • Felix: Energetic, promo
  • Nova: Bright, upbeat

Neutral News and Explainers

Maintain professionalism with neutral, authoritative voices. Atlas delivers a neutral news style, while Milo offers a friendly, conversational tone. Sage is perfect for instructional content, providing a calm, clear delivery that aids comprehension.

  • Atlas: Neutral, news
  • Milo: Friendly, conversational
  • Sage: Calm, instructional

Support for 23 Languages

Sound wave illustration for: Support for 23 Languages

VoxLocale supports 23 languages, covering major European and Asian markets. You can generate audio for 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 can speak any of these languages, allowing you to maintain consistent character voices across your entire localization pipeline.

European and Asian Markets

Our API handles diverse scripts and phonetic structures, ensuring natural-sounding results for localized content. Whether you are dubbing a documentary into German or creating an ad in Japanese, the same voice presets deliver consistent tone and style across all 23 supported languages.

  • Full support for 23 distinct languages
  • Consistent voice profiles across all regions
  • Ideal for multi-market localization projects

Latin American Spanish

Generate clear, professional Spanish audio for Latin American audiences. The API supports Spanish, allowing you to produce consistent dubbing for videos targeting specific regional markets.

Auto-Detection with Fallback

If you do not specify a language, the system guesses it from the script. Latin-script text defaults to English. For non-English Latin-script text, we recommend setting the language parameter explicitly to ensure accuracy. This fallback mechanism simplifies your API integration while maintaining high quality.

  • Automatic language detection from script
  • Latin text defaults to English
  • Set language param for non-English Latin text

Developer-Friendly API

Sound wave illustration for: Developer-Friendly API

Integrate our TTS engine into your dubbing pipeline using the official OpenAI SDKs. Simply update the base_url to https://api.playyy9.com/v1 and use your API key. This ensures a familiar development experience without requiring a custom client library or complex middleware.

OpenAI SDK Compatible

Leverage existing tools and libraries you already know. By mimicking the OpenAI speech endpoint, we allow you to swap in our engine with minimal code changes. This compatibility extends to the official OpenAI SDKs.

  • Uses standard POST requests for audio generation
  • Compatible with official OpenAI client libraries

Simple JSON Requests

Send your script as a JSON body with fields like model, input, and voice. The API returns the audio file directly, ready for assembly into your video timeline. You can also specify speed and language for precise control over the output.

  • Supports tts-1 and tts-1-hd models
  • Accepts text up to 4096 characters per request

Multiple Audio Formats

Choose from MP3, WAV, OPUS, FLAC, or PCM based on your project needs. Whether you need compressed files for web delivery or lossless formats for post-production, the API delivers the exact format you specify in the response_format field.

  • MP3, WAV, OPUS, FLAC, PCM supported

Transparent Pricing

Sound wave illustration for: Transparent Pricing

Pricing is straightforward: $0.01 per 1,000 characters, with spaces and punctuation counting toward the total. This character-based model ensures you only pay for the actual content processed, making it easy to predict costs for large-scale dubbing projects without hidden fees.

Pay Per Character

Each request is charged based on the input length. For example, a 4,000-character script costs just $0.04. This transparency allows agencies to predict costs.

  • $0.01 per 1,000 characters
  • Spaces and punctuation count
  • No minimum spend

No Monthly Fees

There are no subscriptions, seats, or recurring costs. You top up your balance with USDT (TRC-20) when needed. Credits never expire, so you can pause production and resume later without penalty.

Free Failed Requests

If synthesis fails, you are not charged. The full amount is returned to your balance. This ensures you only pay for successful audio generation, reducing risk during testing or high-load periods.

Transparent Pricing

Technical Specifications

Sound wave illustration for: Technical Specifications

Each API request accepts a maximum of 4096 characters, including spaces and punctuation. For longer scripts, split the text into parts and join the resulting audio files sequentially. This ensures consistent audio quality regardless of script length.

4096 Character Limit

The input field accepts up to 4096 characters per request. For scripts exceeding this limit, split the text into smaller chunks. Generate audio for each chunk and join the files to create the final track. This method maintains audio continuity and avoids truncation errors.

  • Max 4096 characters per request
  • Split and join for longer scripts
  • Includes spaces and punctuation

Speed Control 0.25x-4.0x

Adjust the playback speed between 0.25 and 4.0 to match the original video's timing. This allows precise lip-sync adjustments without re-recording. Faster speeds reduce generation time, while slower speeds enhance clarity for complex dialogue.

  • Range: 0.25x to 4.0x
  • Fine-tune lip-sync
  • Adjustable per request

MP3, WAV, FLAC, OPUS, PCM

Choose from five audio formats: MP3, WAV, FLAC, OPUS, and PCM. Select the format that best fits your post-production workflow. MP3 and OPUS offer small file sizes, while WAV and FLAC provide lossless quality for professional editing.

  • MP3, WAV, FLAC, OPUS, PCM
  • Lossless and compressed options
  • Fit any post-production workflow

Why Agencies Choose Us

Sound wave illustration for: Why Agencies Choose Us

VoxLocale delivers synthetic voice output without the complexity of training custom voice models. By leveraging our eight preset voices across 23 languages, agencies can maintain brand consistency across dubbing projects without needing to manage multiple voice-cloning pipelines or negotiate individual talent rights.

No Voice Cloning Needed

Our API uses eight distinct, licensed voices (e.g., Aria, Felix, Atlas) that cover diverse tones from warm narration to energetic promos. This eliminates the need for custom voice cloning, reducing setup time and ensuring predictable audio quality across all your localization projects.

Inaudible Watermarks

Every generated audio file contains an inaudible watermark marking it as synthetic speech. This provides clear provenance for your dubbing assets, helping you maintain transparency with clients and platforms regarding AI-generated content without affecting the listening experience.

Privacy-Focused Data

Your input text is used solely to produce the audio and is not used for training our models. Generated audio is returned in the response and not stored on our servers, ensuring your script data remains private and secure throughout the production workflow.

Get Started Quickly

Sound wave illustration for: Get Started Quickly

Start by signing up via Google or email on the /get-api-key/ page. Your account is created instantly, and if you use Google sign-in, you receive a $0.50 free trial credit valid for 7 days.

Your unique API key appears immediately on the dashboard alongside your current balance and usage stats. You can generate a new key at any time, which instantly invalidates the old one.

Sign Up with Google

Click the sign-up button and authorize with your Google account. This method grants you immediate access to the $0.50 trial credit (approx. 50,000 characters). Accounts created with email and password do not receive this trial credit.

  • Instant account creation
  • $0.50 trial credit with Google sign-in
  • 7-day validity for trial credit

Get Your API Key

Your API key is displayed on the dashboard. Use it in the Authorization: Bearer header. You can issue a new key at any time; the previous key stops working immediately.

  • Key displayed on /get-api-key/
  • One active key per account
  • Instant invalidation of old keys

Run Your First Request

Use the provided cURL example or the OpenAI SDK with the base URL https://api.playyy9.com/v1. Send a POST request to /v1/audio/speech with your text, chosen voice, and model. Receive the audio file directly in the response.

  • Use OpenAI SDK or plain HTTP
  • Base URL: https://api.playyy9.com/v1
  • Endpoint: POST /v1/audio/speech

FAQ for Agencies

Sound wave illustration for: FAQ for Agencies

For agencies managing high-volume dubbing projects, understanding technical constraints and billing behaviors is essential for smooth integration. Our API is designed to handle the specific workflows of localization teams, from character limits to error handling, ensuring you can predict costs and performance accurately.

Can I use my own voice data?

No, we do not offer custom voice cloning or the ability to upload your own voice recordings. We provide eight distinct, licensed presets derived from LibriTTS-R and LibriVox public-domain readings. These voices are fixed and cannot be modified or trained on new audio.

Do you offer SLA?

We do not provide Service Level Agreements, uptime guarantees, or enterprise contracts. Our infrastructure is optimized for cost-effective, character-based usage rather than guaranteed availability. Support is available via email only, with no live chat or phone support options.

How do I handle long scripts?

Each API request supports a maximum of 4,096 characters. For scripts exceeding this limit, you must split the text into smaller parts, generate audio for each segment, and join the resulting audio files. Failed requests do not incur charges, so splitting large scripts is risk-free.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Unlike many consumer-grade platforms, we do not use your input text to train our models.

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

More on this site