---
title: "Multilingual speech-to-text API for 14 languages | BroadRouter"
description: "Transcribe English, Spanish, French, Chinese, Arabic and 9 more languages through one OpenAI-compatible endpoint priced per minute, and when to use the Arabic model."
url: https://broadrouter.com/blog/multilingual-speech-to-text-api/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Multilingual speech-to-text API: 14 languages, one endpoint

By the BroadNet Inference team · 6 min read · Published 2026-11-14 · Updated 2026-11-16

BroadNet Transcribe is a speech-to-text model for 14 languages, including English, Spanish, French, German, Chinese, Japanese and Arabic, served on an OpenAI-compatible /v1/audio/transcriptions endpoint. It costs $0.002 per audio minute ($0.12 per hour). For mainly Arabic audio, BroadNet Transcribe Arabic is the specialised option at $0.0042 a minute.

## Key takeaways

-   BroadNet Transcribe covers 14 languages: en, es, fr, de, it, pt, el, nl, pl, zh, ja, ko, vi and ar.
-   Price: $0.002 per audio minute, $0.12 per audio hour.
-   Send the language code with every request; do not rely on auto-detection.
-   Choose BroadNet Transcribe Arabic ($0.25 per hour) when Arabic audio is your main workload; BroadNet publishes Arabic accuracy numbers for that model.
-   Same limits for both: WAV or MP3, up to 26,214,400 bytes per file, no audio or transcript retained.

**On this page**

1.  Which languages does BroadNet Transcribe cover?
2.  How much does multilingual transcription cost?
3.  How do you call the transcription endpoint?
4.  Why should you always send the language?
5.  What are the limits and formats?
6.  When should you choose the Arabic-specific model?
7.  How do you test accuracy in each language?
8.  What workloads does it suit?
9.  What happens after transcription?
10.  How do you migrate from another transcription API?

_[image: The words English, Español, Français, Deutsch, 日本語, 한국어, 中文, Tiếng Việt and العربية, with the text "Many languages. One connection."]_

Most products that handle audio deal with more than one language: a global support line, meeting recordings from different offices, a voice-note inbox in a multilingual city. Running one speech-to-text vendor per language is a maintenance cost. BroadNet Transcribe puts 14 languages behind one OpenAI-compatible endpoint, priced per audio minute, with a specialised Arabic model next to it for Arabic-heavy workloads.

## Which languages does BroadNet Transcribe cover?

The language list comes from BroadNet’s published [pricing.json](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-multilingual-speech-to-text-api&utm_content=body), as ISO 639-1 codes:

| Code | Language | Code | Language |
| --- | --- | --- | --- |
| en | English | nl | Dutch |
| es | Spanish | pl | Polish |
| fr | French | zh | Chinese |
| de | German | ja | Japanese |
| it | Italian | ko | Korean |
| pt | Portuguese | vi | Vietnamese |
| el | Greek | ar | Arabic |

[BroadNet Transcribe](https://broadrouter.com/models/cohere-transcribe/) is based on Cohere Transcribe and is served by BroadNet. The model id is `broadnet/cohere-transcribe`.

For the full picture, our open [speech-to-text API price index](https://broadrouter.com/data/speech-to-text-api-prices/) lists batch and streaming prices, billing increments and Arabic support for more than 20 products, each checked against the provider’s own pricing page (CSV and JSON).

## How much does multilingual transcription cost?

| Model | Per minute | Per hour | Languages |
| --- | --- | --- | --- |
| [BroadNet Transcribe](https://broadrouter.com/models/cohere-transcribe/) | $0.002 | $0.12 | 14 |
| [BroadNet Transcribe Arabic](https://broadrouter.com/models/cohere-transcribe-arabic/) | $0.0042 | $0.25 | Arabic |

Billing is per minute of audio, not per request or per token. Both models work on the free $5 starting credit, so you can test your own recordings before topping up. See all prices on the [pricing page](https://broadrouter.com/pricing/), price your monthly hours in the [speech-to-text cost calculator](https://broadrouter.com/tools/speech-to-text-cost-calculator/), or compare other providers in [speech-to-text API pricing compared](https://broadrouter.com/blog/speech-to-text-api-pricing-compared/).

## How do you call the transcription endpoint?

The endpoint follows the OpenAI audio transcription shape, so the official SDKs work with a changed base URL:

```python
import os
from openai import OpenAI

client = OpenAI(base_url="https://inference.broadnet.ai/v1", api_key=os.environ["BROADNET_API_KEY"])

with open("meeting-fr.mp3", "rb") as audio:
    result = client.audio.transcriptions.create(
        model="broadnet/cohere-transcribe",
        file=audio,
        language="fr",
    )
print(result.text)
```

Or with curl:

```bash
curl https://inference.broadnet.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $BROADNET_API_KEY" \
  -F model=broadnet/cohere-transcribe \
  -F language=es \
  -F file=@llamada.wav
```

The response is JSON with the transcript in `text`. BroadNet’s documented response is the text itself; if you need word timestamps or speaker labels, check the [API reference](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-multilingual-speech-to-text-api&utm_content=body) for what is currently supported before you design around them.

## Why should you always send the language?

BroadNet’s docs are explicit: send `language` with every transcription request. Without it, Arabic can come back transliterated into Latin letters, and the same risk applies to any language the model might confuse. If you do not know the language in advance:

1.  **Use metadata first.** The caller’s country, the user’s app language or the phone number prefix is usually right.
2.  **Ask the user** in voice products (“press 1 for English, 2 for Arabic”).
3.  **Try a short sample.** Transcribe the first 30 seconds with your best guess; if the text looks wrong (wrong script, gibberish), retry with the next candidate.

## What are the limits and formats?

-   **Formats:** WAV (`audio/wav`) or MP3 (`audio/mpeg`). Convert .ogg, .m4a, .webm and video files with ffmpeg first. The [WhatsApp voice-note guide](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/) has the one-liner.
-   **Size:** up to 26,214,400 bytes (25 MiB) per file; larger files return 413. That is about 13 minutes of 16 kHz mono WAV or about 54 minutes of 64 kbit/s MP3. Split longer audio with `ffmpeg -f segment -segment_time 600`.
-   **Rate:** a pay-as-you-go key allows 30 requests a minute and 4 at once. Retry 429 with backoff; see [errors and retries](https://broadrouter.com/guides/errors-and-retries/).
-   **Privacy:** audio and transcripts are processed for the request and not retained. See [zero data retention](https://broadrouter.com/zero-data-retention/).

For a production batch pipeline with chunking and a worker pool, see [Arabic call-centre transcription at scale](https://broadrouter.com/blog/transcribe-call-center-recordings/); the same design works for any of the 14 languages.

## When should you choose the Arabic-specific model?

BroadNet offers two models because Arabic is harder than most languages for speech recognition: many dialects under one written standard, frequent code-switching with English and French, and a lot of phone-quality audio. BroadNet Transcribe Arabic is the specialised option, and BroadNet publishes Arabic accuracy only for it:

-   BroadNet reports it at #2 of 37 (its September 2026 figure; the live board listed it #4 of 39 on 15 November 2026) on the [Open Universal Arabic ASR Leaderboard](https://huggingface.co/spaces/elmresearchcenter/open_universal_arabic_asr_leaderboard), and #1 among models whose licences permit API serving.
-   BroadNet’s lab word error rates: 3.8 on FLEURS-ar, 21.1 on MASC-ar and 23.4 on its dialect set (lower is better). [What those numbers mean](https://broadrouter.com/blog/arabic-asr-wer-explained/).

BroadNet does not publish Arabic numbers for the 14-language model, but the public leaderboard does: on 15 November 2026 it listed Cohere Transcribe 03-2026, the model behind BroadNet Transcribe, at #8 of 39 with an average WER of 30.67, against 24.19 for the Arabic model at #4 of 39. For other languages, BroadNet reports 5.5 word error rate on FLEURS English and 3.2 on FLEURS Spanish for BroadNet Transcribe, and about 113 times realtime on one stream (217 times batched) on English audio, per its [model page](https://www.broadnet.ai/inference/models/cohere-transcribe). A simple rule:

| Your audio | Choose |
| --- | --- |
| Mostly Arabic, any dialect | BroadNet Transcribe Arabic |
| Arabic is a minority of files, accuracy is not critical | BroadNet Transcribe for everything, or test both |
| Mixed portfolio with a known language per file | Route Arabic files to the Arabic model, the rest to BroadNet Transcribe |
| Any of the other 13 languages | BroadNet Transcribe |

Routing by language is a one-line change, since both models share the endpoint and request shape:

```python
def stt_model(lang: str) -> str:
    return "broadnet/cohere-transcribe-arabic" if lang == "ar" else "broadnet/cohere-transcribe"
```

The Arabic model costs about twice as much per minute. At volume, test both on a few hours of your real Arabic audio and compare word error rate per dialect; the [Arabic speech-to-text buyer’s guide](https://broadrouter.com/blog/arabic-speech-to-text-api-buyers-guide/) has a one-hour test plan. If numbers, dates and names in noisy Arabic audio are the problem, BroadNet also lists a fine-tuned Arabic model on request on the [models page](https://broadrouter.com/models/).

## How do you test accuracy in each language?

A single vendor accuracy figure hides big differences between languages, accents and recording conditions. Before you commit a workload, run a small test per language:

1.  **Collect 20 to 50 real clips per language,** from the channel you will actually transcribe: phone calls, meeting recordings, voice notes or video. Include your hardest accents.
2.  **Write reference transcripts** for a subset by hand, with agreed spelling rules for numbers, names and English loanwords.
3.  **Transcribe with the correct `language` code** and compute [word error rate](https://broadrouter.com/glossary/word-error-rate/) per language. For Chinese and Japanese, which are written without spaces between words, use character error rate instead.
4.  **Read the errors.** Product names, amounts and addresses matter more than filler words.
5.  **Repeat for Arabic with both models** if Arabic is part of your mix, and compare per dialect.

The $5 starting credit covers a test like this for several languages on BroadNet Transcribe, because the per-minute price is low.

## What workloads does it suit?

| Workload | Notes |
| --- | --- |
| Multilingual support lines | Route by the IVR language choice; send the matching `language` code |
| Meeting notes for distributed teams | Transcribe per recording, then summarise with an LLM |
| Voice-note inboxes | Convert .ogg to WAV first; see the WhatsApp guide |
| Media and podcast archives | Split long files under 25 MiB; batch overnight |
| Language-learning apps | Transcribe learner speech, then give feedback with an LLM |

In every case the cost scales with audio minutes only: $0.12 per hour of audio on BroadNet Transcribe, whatever the language.

## What happens after transcription?

Transcripts are rarely the end product. Common next steps on the same API key:

-   **Summaries and action items** for meetings with [DeepSeek V4.1 Flash](https://broadrouter.com/models/deepseek-v4.1-flash/), whose 1,048,576-token context fits very long transcripts.
-   **Translation** of transcripts into one working language; see [Arabic–English translation with LLMs](https://broadrouter.com/blog/arabic-english-translation-llm/).
-   **QA scoring** of support calls with structured JSON output.

## How do you migrate from another transcription API?

If you already call an OpenAI-style transcription endpoint, including the Whisper API that OpenAI lists as shutting down on February 26, 2027 ([what to test before you switch](https://broadrouter.com/blog/whisper-api-alternative/)), migration is usually three changes: base URL, API key and model id, plus making sure you send `language`. Check response fields your code reads beyond `text`. The [OpenAI-compatible migration checklist](https://broadrouter.com/blog/openai-compatible-api-migration-checklist/) covers the rest.

Free tools for this

-   [Arabic token counter](https://broadrouter.com/tools/arabic-token-counter/) Arabic vs English token counts per tokenizer: the "Arabic tax" in tokens and money.
-   [Arabic text normalizer](https://broadrouter.com/tools/arabic-text-normalizer/) Tashkeel, tatweel, alef, ya, ta marbuta, digits and invisible characters, with a matching Python function.
-   [Speech-to-text cost calculator](https://broadrouter.com/tools/speech-to-text-cost-calculator/) Hours, calls or voice notes to a monthly transcription bill, against your current provider.

[All free tools](https://broadrouter.com/tools/)

## Terms in this article

[Speech-to-text](https://broadrouter.com/glossary/speech-to-text/)

Speech-to-text, also called automatic speech recognition (ASR), is technology that converts spoken audio into written text. A speech-to-text API accepts an audio file or stream and returns a transcript, usually priced per minute of audio. Accuracy is measured with word error rate and varies with accent, dialect and recording quality.

[Word error rate](https://broadrouter.com/glossary/word-error-rate/)

Word error rate (WER) is the standard accuracy measure for speech recognition: the number of word substitutions, deletions and insertions needed to turn a transcript into the correct reference, divided by the number of words in the reference. Lower is better.

[Pay-as-you-go](https://broadrouter.com/glossary/pay-as-you-go/)

Pay-as-you-go is a pricing model in which you pay only for what you use, metered per unit such as tokens, requests or audio minutes, with no subscription or minimum commitment. Most LLM APIs bill this way, from a prepaid balance or a periodic invoice.

[WAV](https://broadrouter.com/glossary/wav/)

WAV (Waveform Audio File Format, or WAVE) is an audio container built on Microsoft and IBM's RIFF format. It usually holds uncompressed linear PCM samples, so its size is predictable: sample rate times bytes per sample times channels, per second.

[API key](https://broadrouter.com/glossary/api-key/)

An API key is a secret string that identifies and authorizes a client calling an API. LLM APIs usually expect it in an Authorization: Bearer header, and anyone who holds the key can make requests that are billed to the account that owns it.

[Base URL](https://broadrouter.com/glossary/base-url/)

A base URL is the fixed root address of an API, such as https://api.example.com/v1, that a client puts in front of every endpoint path, such as /chat/completions. In OpenAI-compatible SDKs, changing the base URL, together with the API key and model ID, points the same code at a different provider.

[Ogg Opus](https://broadrouter.com/glossary/ogg-opus/)

Ogg Opus is audio encoded with the Opus codec (RFC 6716) and stored in an Ogg container (RFC 7845). It is built for speech and interactive audio at low bitrates, and it is the format WhatsApp uses for voice notes, usually as .ogg or .opus files.

[Character error rate (CER)](https://broadrouter.com/glossary/character-error-rate/)

Character error rate (CER) measures transcription or OCR accuracy at the character level: the substitutions, deletions and insertions needed to turn the output into the reference text, divided by the number of characters in the reference. Lower is better, and 0 is a perfect match.

## Questions

### Which languages does BroadNet Transcribe support?

Fourteen - English, Spanish, French, German, Italian, Portuguese, Greek, Dutch, Polish, Chinese, Japanese, Korean, Vietnamese and Arabic. The list is published in pricing.json as ISO 639-1 codes.

### Can one file contain two languages?

Each request takes one language code. For audio that switches languages, transcribe with the main language and check how the other language comes out, or split the audio by speaker or segment if the switches are long.

### Is the multilingual model good enough for Arabic?

It accepts Arabic and costs less per minute. BroadNet publishes Arabic accuracy figures only for BroadNet Transcribe Arabic, so if Arabic is a large share of your audio, test both on your recordings and compare word error rate.

### Does it work with the OpenAI SDK?

Yes. Point the SDK at the BroadNet base URL and call audio.transcriptions.create with the model id, the file and the language.

## Keep reading

-   [Transcribe long audio over 25 MB: split, send and stitch](https://broadrouter.com/blog/transcribe-long-audio-files-api/)
-   [Arabic speech-to-text API: how to choose one in 2026](https://broadrouter.com/blog/arabic-speech-to-text-api-buyers-guide/)
-   [Arabic ASR word error rate (WER) explained](https://broadrouter.com/blog/arabic-asr-wer-explained/)
-   [How to transcribe call center recordings: an Arabic-ready pipeline](https://broadrouter.com/blog/transcribe-call-center-recordings/)
-   [Switching to an OpenAI-compatible API: a migration checklist](https://broadrouter.com/blog/openai-compatible-api-migration-checklist/)
-   [Add diacritics to Arabic text with an LLM: prompt, checks, DER](https://broadrouter.com/blog/arabic-diacritization-llm/)
-   [Arabic grammar and spelling correction with an LLM: a how-to](https://broadrouter.com/blog/arabic-grammar-spelling-correction-llm/)
-   [Guide: Arabic speech-to-text API, step by step](https://broadrouter.com/guides/arabic-speech-to-text-api/)
-   [Guide: Transcribe WhatsApp voice notes to text with an API](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/)
-   [Guide: BroadNet Inference error codes and when to retry](https://broadrouter.com/guides/errors-and-retries/)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-multilingual-speech-to-text-api&utm_content=page-cta) ·

**Sources**

-   [BroadNet Transcribe model page: FLEURS English and Spanish WER, throughput (fetched 2026-11-15)](https://www.broadnet.ai/inference/models/cohere-transcribe)
-   [Open Universal Arabic ASR Leaderboard, live table (fetched 2026-11-15)](https://huggingface.co/spaces/elmresearchcenter/open_universal_arabic_asr_leaderboard)
-   [BroadNet Inference API reference, transcription (checked 2026-11-16)](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-multilingual-speech-to-text-api&utm_content=sources)
-   [BroadNet Inference machine-readable prices and language list (pricing.json, checked 2026-11-16)](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-multilingual-speech-to-text-api&utm_content=sources)
-   [BroadNet model catalogue, speech to text (checked 2026-11-16)](https://www.broadnet.ai/inference/models)
-   [ISO 639 language codes (Library of Congress, checked 2026-11-16)](https://www.loc.gov/standards/iso639-2/php/code_list.php)
