Text to Speech Tool for Localization Freelancers

By DubSync editorial team · Updated 2026-11-18

DubSync API is a cloud text-to-speech engine built for freelancers and agencies handling localization projects. Send text and receive audio files via a simple API that fits directly into your existing dubbing workflow. We provide consistent voice quality across episodes and fast turnaround times for client deliveries.

This page explains how our OpenAI-compatible endpoint, 23 languages, and 8 voice presets help you produce professional voiceovers efficiently. Explore our technical specs, transparent pricing, and data privacy terms to see if our TTS API matches your localization needs.

Text to Speech Tool for Localization Freelancers

Frequently asked questions

What is the character limit per request?

Each API request supports up to 4096 characters of input text. If your script exceeds this limit, you must split the text into smaller parts and send multiple requests. The API processes these sequentially, so you will need to join the resulting audio files to create the final complete voiceover track.

Which languages are supported for dubbing?

We support 23 languages including English, Spanish, French, German, Japanese, Korean, Arabic, and Hindi. Any voice can speak any of these languages. If you do not specify the language, the system guesses it based on the script, but setting it explicitly is recommended for non-English Latin-script text.

How does the speed control affect voice quality?

You can adjust the speed between 0.25 and 4.0 using the speed parameter. This allows you to match pacing for different dubbing needs. The engine maintains voice consistency across these speeds, ensuring the output remains clear and natural whether you are slowing down narration or speeding up dialogue.

Is there a limit on the number of voices I can use?

You can use all 8 available voices: Aria, Nova, Luna, Sage, Felix, Milo, Atlas, and Orion. There is no limit on how many different voices you can call in your requests. You can switch voices dynamically between requests to create diverse character voices for your dubbing projects.

Can I generate audio in multiple formats simultaneously?

You can choose from mp3, wav, opus, flac, or pcm for each request. However, each request generates only one file in one format. To get multiple formats, you must send separate requests for the same text with different response_format values. The API does not return multiple formats in a single response.

How long is my API key valid?

Your API key does not expire. It remains active as long as you have a valid account. You can issue a new key at any time, which immediately invalidates the old one. This ensures you can rotate keys for security without losing access to your balance or usage history.

Do I need to pay for failed requests?

No, failed requests are free. If synthesis fails for any reason, the charge is returned in full to your balance. You only pay for successful audio generations. This protects your budget when testing voices or handling edge cases in your dubbing workflow.

Is the audio generated commercially usable?

Yes, the audio is generated from licensed recordings and public-domain sources. However, every file includes an inaudible watermark marking it as synthetic speech. This watermark identifies the audio as AI-generated. You retain the rights to use the generated audio in your projects.

How do I split long texts for synthesis?

Split your text into chunks of up to 4096 characters. Send each chunk as a separate POST request to the speech endpoint. Once you receive all audio files, join them in your preferred audio editor or script. This ensures each request stays within the character limit and processes efficiently.

Can I change the voice after generation?

No, you cannot change the voice after the audio is generated. Each request produces audio with a specific voice preset. To use a different voice, you must send a new request with the voice parameter set to your desired preset. The original audio file remains unchanged.

What happens if I exceed my character limit?

If your input text exceeds 4096 characters, the request will fail. You must split the text into smaller parts yourself before sending. The API does not automatically split long texts. Ensure each request contains 4096 characters or fewer to guarantee successful synthesis and accurate billing.

Is there a minimum charge for top-ups?

Yes, the minimum top-up amount is $5. Payments are made via USDT on the TRON network (TRC-20). Funds are credited automatically within minutes after the transfer. There are no monthly plans or minimum spend requirements, so you only pay for what you need when you need it.

How do I know if my request was successful?

The API returns the audio file directly in the response body upon success. If the request fails, you will receive an error response with a status code and message. Failed requests are also free, so you can retry without worrying about extra charges.

Can I use this tool for audiobook production?

Yes, the tool is suitable for audiobook production. You can use voices like Luna for storytelling or Atlas for news. Since input is limited to 4096 characters per request, you must split longer chapters into segments. Join the resulting audio files to create the final audiobook track.

First request

curl

curl https://api.playtk71.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 dubbing pros choose our TTS API

Sound wave illustration for: Why dubbing pros choose our TTS API

Dubbing agencies and freelancers often face tight deadlines where waiting for human voice actors or slow rendering tools means missed delivery windows. Our API delivers audio files in seconds, allowing you to iterate quickly on client scripts without bottlenecking your production schedule.

When working on series or episodic content, maintaining character consistency is critical. With eight distinct voice presets available, you can assign a specific voice to a character and regenerate lines anytime, ensuring the tone remains identical across every episode without re-hiring talent.

Fast turnaround for client projects

Fast turnaround for client projects

Text-to-speech generation is typically real-time, meaning you receive the audio file almost as fast as you type. This speed allows you to test multiple interpretations of a script in minutes rather than hours, accelerating your review cycle with clients.

  • Receive audio files within seconds for short phrases
  • Process longer texts at roughly real-time speed
  • Iterate on script changes without waiting days

Consistent voice across episodes

You can lock in a specific voice preset for a character and reuse it indefinitely. If a line needs re-recording due to a script change, the voice will sound identical to previous takes, maintaining narrative continuity without the variability of human performance.

This consistency is vital for localization workflows where multiple translators or editors might refine the same script over weeks. The voice remains the anchor, ensuring the final product feels cohesive.

  • Use the same voice preset for recurring characters
  • Regenerate lines with identical tone and timbre
  • Maintain character integrity across long series

Easy integration with your workflow

The API endpoint follows the standard JSON structure used by major platforms, so you can integrate it directly into your existing scripts or automation tools with minimal code. Just update the base URL and insert your API key.

Whether you are building a custom localization dashboard or using simple curl commands, the setup is straightforward. You send the text, and the API returns the audio file ready for your editing software.

Adjust speed from 0.25x to 4.0x to match lip-sync requirements or pacing needs without needing post-production audio stretching tools.

  • Compatible with standard OpenAI SDKs
  • JSON request body, simple to automate
  • Adjustable speed for precise lip-sync

Supported languages and voice presets

Sound wave illustration for: Supported languages and voice presets

DubSync API supports 23 languages, covering major markets like Spanish, German, and Japanese. Any voice can speak any of these languages, ensuring consistent quality across your entire dubbing catalog.

23 languages including Spanish, German, and Japanese

We support 23 languages, including Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.

8 distinct voice personalities for diverse characters

Choose from 8 presets: Aria, Nova, Luna, and Sage for female roles; Felix, Milo, Atlas, and Orion for male roles. Voices are based on licensed LibriTTS-R recordings and LibriVox public-domain audiobook readings.

  • Aria: warm, clear narrator
  • Felix: energetic, promo
  • Atlas: neutral, news
  • Orion: deep, documentary

Auto-detection with manual language override

If you do not set the language, the system guesses it from the script, defaulting to English for Latin text. For non-English Latin-script text, always set the language parameter to ensure accuracy.

Technical specs for developers

Sound wave illustration for: Technical specs for developers

The API endpoint POST https://api.playtk71.com/v1/audio/speech accepts standard JSON bodies, allowing you to use official OpenAI SDKs by simply changing the base URL. This compatibility means your existing localization scripts can connect immediately without learning a new client structure.

Each request accepts text up to 4096 characters, returning synthesized audio directly in the response. Failed requests incur no charge, ensuring you only pay for usable voiceovers delivered to your dubbing pipeline.

OpenAI-compatible JSON endpoint

Send text via POST https://api.playtk71.com/v1/audio/speech with a JSON body containing model, input, voice, and other parameters. The authentication header Authorization: Bearer tts-... works exactly like OpenAI’s, so you can swap the base_url and reuse your existing code.

Multiple audio formats: MP3, WAV, OPUS, FLAC

Choose between MP3, WAV, OPUS, or FLAC to match your production environment. MP3 offers small file sizes for quick reviews, while WAV and FLAC provide lossless quality for final master tracks. OPUS is ideal for efficient streaming or web-based dubbing projects.

Speed control from 0.25x to 4.0x

Adjust the speed parameter between 0.25 and 4.0 to fit voiceovers precisely into video timelines. This flexibility helps synchronize speech with lip movements without needing complex post-production time-stretching, saving hours of editing time for each localized episode.

Transparent pricing for agencies

Sound wave illustration for: Transparent pricing for agencies

Agency budgets depend on predictability. Our TTS API charges a flat $10 per 1 million characters, which equals $0.01 per 1,000 characters. Spaces and punctuation count toward this limit, so your cost calculation is exact from the first character.

$10 per million characters

The rate is consistent regardless of voice or model. Whether you use tts-1 or tts-1-hd, the character count determines the cost. This simplicity helps you quote dubbing projects accurately to clients without worrying about variable engine costs.

No hidden fees or monthly subscriptions

You pay only for what you use. There are no monthly plans, no seats, and no minimum spend. You do not need to manage subscriptions or worry about unused credits expiring. Your balance never expires, allowing you to top up only when needed.

Pay only for successful generations

If a synthesis request fails, you are not charged. The cost is returned in full, so you only pay for usable audio. This protects your budget when processing large volumes of dialogue for localization projects.

How it works

Sound wave illustration for: How it works

Getting started is straightforward: create an account on our site using either your Google credentials or a standard email and password combination. Once registered, you are directed to your dashboard where your unique API key is generated and displayed immediately.

From there, you can view your balance and test the service. The process is designed to get you from zero to your first generated audio file in minutes, allowing you to integrate DubSync into your dubbing workflow without delay.

Sign up with Google or email

Create your account in seconds. You can choose to sign in with Google for immediate access, or register using your email address and a password. Each site maintains independent accounts, so ensure you are on playtk71.com to access your specific credentials.

Get your API key instantly

Your dashboard displays your active API key, current balance, and usage statistics immediately after registration. You can issue a new key at any time, which invalidates the old one instantly, ensuring secure access for your team or agency.

Send text and receive audio

Use your key to send a POST request to our endpoint. Provide your script (up to 4096 characters), select a voice and language, and choose your preferred audio format. The API returns the audio file directly, ready for your editing timeline.

  • Supports MP3, WAV, OPUS, FLAC, and PCM formats
  • Handle long scripts by splitting text into 4096-character chunks
  • Adjust speed from 0.25x to 4.0x for precise timing
How it works

Data privacy and usage

Sound wave illustration for: Data privacy and usage

Your input text is processed exclusively for the purpose of generating the requested audio file. We do not repurpose your scripts for other uses, ensuring your creative content remains yours.

The engine does not use your submitted text for model training or improvement. Once the audio is synthesized and delivered, the text itself is discarded, keeping your source material private and secure.

Input text used only for synthesis

When you send a request, the text is temporarily held in memory solely to generate the audio file. It is not indexed, analyzed, or stored beyond what is necessary for immediate processing and billing records.

No training on your content

Unlike some consumer platforms, we do not train our models on your data. Your scripts remain distinct from our training corpus, preserving the uniqueness of your localization projects.

Audio returned in response, not stored

The generated audio file is returned directly in the API response. We do not permanently store the audio files on our servers, meaning you retain full control over your deliverables immediately after generation.

  • Request metadata (time, characters, status) is kept for billing purposes only.
  • No long-term storage of your audio assets.

Quality and licensing

Sound wave illustration for: Quality and licensing

The DubSync API utilizes voice presets derived from the LibriTTS-R dataset, which is licensed under CC BY 4.0. These voices originate from public-domain audiobook readings via LibriVox, ensuring a foundation of licensed, high-quality recordings without the need for complex rights clearance for your base voice assets.

Voices based on licensed LibriTTS-R recordings

Our eight voice presets—ranging from Aria’s warm narration to Orion’s deep documentary tone—are built on these licensed sources. This means you get consistent, professional-grade synthetic voices that are ready for commercial use without worrying about underlying model licensing conflicts.

  • Licenced under CC BY 4.0

Inaudible synthetic watermark in every file

Every audio file generated through the API carries an inaudible watermark that explicitly marks the content as synthetic speech. This feature helps maintain transparency in your dubbing projects, allowing you to clearly identify AI-generated tracks if required by your client contracts or distribution platforms.

Consistent quality across long texts

For longer scripts, the API splits input into parts of up to 4,096 characters and joins the resulting audio files. This approach ensures that the voice character remains consistent throughout your entire project, avoiding the drift or quality drops often seen in other generation methods.

Getting started quickly

Sound wave illustration for: Getting started quickly

Create an account via Google or email on the /get-api-key/ page to receive your unique API key instantly. Your account dashboard displays your key, current balance, and usage statistics, allowing you to start testing immediately without waiting for manual approval.

Use the ready curl example provided on your dashboard to send your first request. Simply replace the placeholder key with your actual key and adjust the input text. This straightforward setup ensures you can integrate the TTS engine into your localization pipeline within minutes.

Free trial credit included

Sign in with Google to receive $0.50 of free trial credit, valid for 7 days. This allows you to generate approximately 50,000 characters to test voice quality and integration before committing funds. Accounts created with email and password do not include this trial credit.

Ready curl examples

The dashboard provides a copy-paste curl command configured for your specific key. It demonstrates the standard JSON body structure, including model, voice, and input fields. This example works directly with the OpenAI SDK by pointing to our base URL, ensuring quick adoption for developers familiar with the format.

Support via email

For technical questions or billing issues, contact us via email. We do not offer live chat or phone support, so please include your API key and request details in your message for faster resolution.

Frequently asked questions

Sound wave illustration for: Frequently asked questions

Frequently asked questions address the specific needs of dubbing freelancers, covering commercial usage, voice options, and technical handling of scripts.

Is this suitable for commercial dubbing?

Yes. Generated audio files are for your client projects. Each file includes an inaudible watermark to mark it as synthetic speech, ensuring transparency if required by your client contracts. You own the output for your localization work.

Can I use my own voice samples?

We do not offer custom voice cloning or uploading of your own voice samples. You must choose from our eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). These are based on licensed LibriTTS-R recordings and are ready to use immediately.

How do I handle long scripts?

Each API request accepts up to 4096 characters. For longer scripts, split the text into parts within this limit, generate each part, and join the resulting audio files. This ensures consistent quality and avoids request timeouts, keeping your production workflow smooth and predictable.

Listen to the 8 voices

Each sample below was generated by this API from the same sentence. Locators master cultural nuance while dubbing artists breathe soul into characters for global audiences.

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. OpenAI API reference: create speech
  3. Creative Commons Attribution 4.0
  4. LibriVox public-domain audiobooks
  5. Python documentation
  6. openai-python on GitHub
  7. W3C WAI: making audio and video accessible
  8. ISO 639 language codes
  9. openai-node on GitHub
  10. LibriTTS-R paper (arXiv 2305.18802)
  11. Node.js documentation
  12. FFmpeg documentation

More on this site