/v1/diacritize
Diacritization
Add Persian short vowels and optional Ezafe while keeping the submitted letters, punctuation, spacing, and ZWNJ intact.
- Marked Persian
- Source-indexed operations
- Optional Ezafe evidence
VowelMarks API
Build Persian reading support into your product.
Add source-preserving diacritics, readable Pinglish, Persian-to-English translation, and Persian speech through one developer interface.
Private developer access. Keys are issued manually.
POST /v1/diacritize
Authorization: Bearer vm_...
{
"text": "کتاب جدید",
"include_ezafe": true
}
// response
{
"original": "کتاب جدید",
"marked": "کِتابِ جَدید",
"operations": [...]
}One key, four capabilities
Use only the Persian support your product needs.
Text endpoints return structured evidence alongside their result. Speech is a separate audio endpoint, and translation remains separate from the reading-cue pipeline.
/v1/pinglish
Pinglish
Turn Persian script into pronunciation-first Latin text using either a readable heritage style or a systematic style.
- Readable or systematic output
- Word alignment
- Pronunciation warnings
/v1/translate
Translation
Translate Persian into English as a separate result so products can preserve Persian as the primary reading surface.
- Persian to English
- Request ID parity
- Separate source and result
/v1/speech
Persian speech
Generate Persian audio with Basic and Premium voices while keeping delivery choices explicit in the request.
- Custom voice presets
- Custom performance direction
- Pace and tone controls
Built for Persian reading products
Give Persian text the reading support your users need.
Use one capability or combine them around the same source passage. VowelMarks keeps Persian script central while your product adds pronunciation, meaning, or audio.
Language learning & edtech
Add marked Persian, Pinglish, translation, and speech to lessons, exercises, and reading tools.
Publishing workflows
Prepare learner-readable Persian and pronunciation guides while retaining the submitted source text.
Speech & voice products
Pair contextual Persian reading cues with generated speech through the same developer interface.
Accessibility & reading tools
Offer layered pronunciation and meaning support without replacing the Persian reading surface.
One integration, layered output
Start with Persian. Return only the help your experience calls for.
A learning app can request marked Persian and Pinglish for a reading view, add English translation on demand, and offer speech from the same passage without combining the results into one opaque response.
Submitted Persianکتاب جدیدت را آماده کن.
Persian reading accuracy
Measured results for the reading engine.
The latest evaluation covers pronunciation, Ezafe, and preservation of the original Persian text. Translation and speech are measured separately.
View accuracy and evaluation methodsPronunciation accuracy2,590 words across 300 Persian sentences
Ezafe precision93.9% recall across 800 Persian sentences
Source text preservedNo source text changes across 337,107 sentences
API pricing
Launch Persian reading features at a predictable cost.
Start with a free evaluation, then scale diacritization, Pinglish, and translation as your usage grows. Persian speech capacity is confirmed with your integration.
How text usage works
- 1×
- Diacritization input character; Ezafe included
- 1×
- Pinglish or pronunciation input character
- 2×
- Persian-to-English translation input character
- Audio
- Speech allowance based on generated audio and voice tier
Each text endpoint is metered separately. Returned marks, metadata, Pinglish, and English output do not count.
Sandbox
$0one-time evaluation
For evaluating and testing an integration before choosing a plan.
- Included
- 50,000 processed characters
- Rate limit
- 10 requests / minute
- Additional usage
- Not available
Builder
$9per month
For prototypes, small learning tools, and low-volume production use.
- Included
- 1 million processed characters / month
- Rate limit
- 60 requests / minute
- Additional usage
- $8 per additional 1M processed characters
Growth
$29per month
For established apps adding Persian reading support to regular workflows.
- Included
- 5 million processed characters / month
- Rate limit
- 180 requests / minute
- Additional usage
- $5 per additional 1M processed characters
Scale
$79per month
For higher-volume platforms that need coordinated capacity planning.
- Included
- 20 million processed characters / month
- Rate limit
- 600 requests / minute
- Additional usage
- $4 per additional 1M processed characters
Additional usage
Need more than your included monthly allowance? Additional processed characters are available at the plan's listed rate. Extra usage is enabled only after confirmation, so you won't be charged automatically for exceeding your allowance.
Monthly processed-character allowances reset each billing cycle and do not roll over.
Need custom capacity or processing terms?
Tell us about monthly text volume, latency needs, regions, and support requirements.
Built for dependable integration
Clear contracts for text, usage, and support.
Source-preserving text
Diacritization returns added marks and source-indexed operations without replacing the submitted Persian letters.
Explicit output layers
Marked Persian, Pinglish, translation, and speech remain separate results, so your product controls when each appears.
Capacity confirmed with you
Keys, endpoint scope, speech allowance, and any additional usage are confirmed before access and charges are enabled.
API questions
Everything you need to know about the VowelMarks API.
Can I generate an API key now?
We issue private API keys after reviewing your use case, expected volume, and data requirements. Contact us to request API access.
Why bill by characters instead of requests?
A request might contain one word or several pages. Input-character billing makes those workloads comparable and prevents short requests from subsidizing unusually large ones.
What counts as a character?
The meter counts Unicode code points in the submitted input, including spaces and punctuation. Diacritization and Pinglish count input characters at 1×; translation counts them at 2×. Added diacritics, metadata, Pinglish output, and English translation output do not count.
Can one key use every endpoint?
Yes. One API key can be scoped to diacritization, Pinglish, translation, and speech. Processing the same text through multiple text endpoints is metered separately for each operation. Speech receives a separate audio allowance confirmed during manual access approval.
Are failed requests billed?
Our policy is to charge successful responses, not validation errors or VowelMarks service failures. Provider-attempt and retry details are confirmed in your access terms before activation.
Is there a production SLA?
Standard developer access is provided without guaranteed uptime SLAs. Enterprise contracts with uptime SLAs, dedicated capacity, or regional data residency are available upon request.
Start with a conversation
Tell us what you want Persian text to do.
Include your product, endpoints, expected text volume, and launch timing. We will reply with fit, capacity recommendations, and integration terms.