New: Soniox v5 Real-Time is here

English to Persian speech translation API

Stream English (English) speech and get Persian (فارسی) back in real time. One WebSocket, ISO codes en to fa, and ultra-low latency for voice agents and live apps.

Trusted by teams building global voice products

Production-ready English to Persian translation API

Real English speech includes accents, regional dialects, code switching, and domain-specific vocabulary. Soniox recognizes it in a single model and streams Persian while the speaker is still talking.

English (Indo-European > Germanic > West Germanic) and Persian (Indo-European > Iranian > Western Iranian) come from different language families, so word order and morphology differ. Soniox reorders meaning in-stream instead of word by word.

English is written in Latin and Persian in Arabic, so Soniox emits correctly scripted Persian text. Right-to-left output is handled directly in the token stream.

A breakthrough in real-time English to Persian translation

Translate before the sentence ends

Persian meaning lands as English is spoken, not after the caption catches up.

Directional en to fa streaming

Set the source and target codes once. Both arrive in a single labeled token stream.

High quality Persian output

Same model across every language, including historically underserved ones.

Native-speaker English STT accuracy

Accurate Persian translation starts with accurate English recognition across accents and language switching.

Names, numbers, and domain terms

Preserved across the pair, including phone numbers, emails, and IDs.

config.json
{
  "model": "stt-rt-v5",
  "translation": {
    "type": "one_way",
    "source_language": "en",
    "target_language": "fa"
  }
}

English and Persian through a single stream

English to Persian translation is built on top of Soniox Speech-to-Text API. Every spoken word is transcribed, and Persian translation streams mid-sentence in the same labeled token stream.

Turn it on by adding a translation block with source_language: "en" and target_language: "fa". It runs on the same WebSocket and the same model, with no extra round trip.

Live English to Persian: written and spoken

English to Persian speech-to-text

Live English speechPersian text

Translate live English into written Persian with the Soniox STT API. Soniox streams the English transcript and the Persian translation as speech happens.

Use it for Persian captions, subtitles, meeting translation, agent assist, and multilingual transcription.

English to Persian speech-to-speech

Live English speechSpoken Persian

Build full spoken English to Persian translation by combining Soniox STT and Soniox TTS. Soniox recognizes English, translates it, and speaks Persian with low latency.

Use it for live interpreters, bilingual voice agents, travel assistants, and customer support.

Live English to Persian translation in action

Stream English to Persian one-way to push all speech into Persian, or two-way to keep a bilingual conversation flowing between the two languages.

English speaker says: Oh, FYI, the client moved the demo to 9:30, so we’re not totally sprinting.
Translated into Persian in real time.

One-way translation

Translate live English into Persian. Everyone in the conversation sees the same translated stream.

Ideal for live captions, multilingual meetings, broadcasts, lectures, and customer calls.

English speaker talks in English.
Persian speaker hears Persian.
Persian speaker replies in Persian.
English speaker hears English.

Two-way translation

Translate between English and Persian for live bilingual conversation. Each side speaks naturally and hears the other in their own language.

Soniox supports real-time two-way translation between any two of 60+ supported languages.

Accurate on both ends of the pair

Soniox transcribes English at 1.25% word error rate and Persian at 1.25% word error rate. Accurate recognition on both sides is what makes the translation reliable.

Speech-to-Text

Native-speaker accuracy across 60+ languages, with support for multilingual speech, alphanumerics, speaker diarization, context.

Translation

Real-time streaming translation across 3,600 language pairs, built for high quality and low delay across all supported languages.

Text-to-speech

High-fidelity speech generation in 60+ languages, built for names, alphanumerics, language switching, and ultra-low-latency streaming.

Together, they create a complete real-time low-latency speech AI platform.

About English and Persian

English has roughly 1,500,000,000 speakers across United States, United Kingdom, Canada, and Australia. Persian has roughly 110,000,000 speakers across Iran, Afghanistan, and Tajikistan.

English is the most widely spoken language in the world when including both native and non-native speakers.

Persian is one of the world's oldest literary languages, with a written tradition spanning over 2,500 years.

Soniox makes English to Persian usable in real-time translation across every supported pair.

Frequently asked questions

How do I translate English to Persian with the API?
Add a translation block to your real-time request with source_language "en" and target_language "fa". Soniox transcribes English and streams the Persian translation over the same WebSocket.
Is English to Persian translation real-time?
Yes. Soniox streams Persian while English is still being spoken, so meaning arrives mid-sentence instead of after the sentence ends.
What about translating Persian to English?
That direction is supported too. See the Persian to English page, or use two-way translation to run both directions in one session.
Does Soniox handle Latin to Arabic output?
Yes. Soniox outputs correctly scripted Persian text in Arabic, including right-to-left rendering, directly in the token stream.
Does Soniox handle English dialects and accents?
Yes. Soniox handles English dialects like American English, British English, and Australian English in a single model, so Persian translation stays accurate across regions.
Which other providers support English to Persian?
Based on their public docs, OpenAI, Google, and Azure list both English and Persian for real-time translation. Soniox is the only one that also supports two-way live translation across 60+ languages.
How fast is English to Persian translation?
Soniox streams Persian as English is being spoken, with ultra-low latency. Translation arrives before the sentence ends.

Simple, usage-based pricing

Translate live audio from English to Persian from ~$0.18/hour.

Translation is already built into Soniox Speech-to-Text API. When turned on, it adds about ~$0.06/hour in output token costs.

Ready to get started?

Create an account instantly, or contact us to design a custom package for your business.

Build with API

Documentation

Get up and running in minutes and spend your time building the product, not wrestling with the API.

Explore docs

See what you’ll pay

Pay only for what you use with our flexible pricing. Built to scale with you.

Pricing details