BroadRouter
Get started

Try BroadNet Inference in your browser, no account

Updated

Open broadnet.ai/inference/playground. It calls the live API through a shared key, with no sign-up or card. Four modes: text chat with Gemma 4, a photo with a question, voice (up to 60 seconds of Arabic or English, returned as a transcript and summary) and documents (an invoice, ID or flyer returned as JSON). BroadNet says request and response content is not retained.

BroadNet runs a free browser playground for BroadNet Inference. It calls the live API through a shared key, so you can hear the Arabic transcription model on your own voice or test a document before you create an account. BroadNet says request and response content is not retained.

What can you try?

The playground has four modes:

Mode What you give it What comes back
Text A question in Arabic or English A streamed answer from Gemma 4
Vision One image, such as a menu, form or handwritten note, plus a question An answer about the image
Voice A recording or upload of up to 60 seconds, Arabic or English A transcript, then a summary
Documents One image of an invoice, ID card, flyer or other document The fields as JSON

Voice accepts WAV up to 4 MB or WebM up to 1.44 MB. That is a playground limit; the API takes WAV or MP3 up to 25 MiB per file.

How do you test Arabic speech to text?

  1. Open the voice mode.
  2. Pick العربية for Arabic or English.
  3. Record up to a minute, or upload a short voice note.
  4. Run the demo and read the transcript and summary.

Try the audio you will really send: a WhatsApp note recorded outside, a phone call, a dialect you care about. A clean read sentence tells you little; BroadNet’s own numbers show the same model at 3.8 word error rate on clean read speech and 23.4 on dialect speech. See what Arabic WER means.

How do you test document reading?

Open the documents mode, choose the document type, upload one image and run it. Check the numbers against the original: totals, dates, ID numbers and phone numbers are where extraction goes wrong. For the same job over the API, see reading Arabic invoices with a vision model.

How do you move the same test to the API?

The playground is for a first look. For real tests you need your own key:

  1. Create an account at inference.broadnet.ai. New accounts get $5 of credit with no card.
  2. Create an API key in your account.
  3. Send the same request with curl or any OpenAI SDK. For a voice note:
curl https://inference.broadnet.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $BROADNET_API_KEY" \
  -F model=broadnet/cohere-transcribe-arabic \
  -F language=ar \
  -F file=@voice-note.wav

Always send language; without it, Arabic can come back in Latin letters. Convert .ogg or .m4a voice notes to WAV first, because the API accepts WAV and MP3 only:

ffmpeg -i voice-note.ogg -ar 16000 -ac 1 voice-note.wav

For chat and images, the curl quickstart has a first request for each endpoint.

What are the limits of a playground test?

  • One file at a time. It shows quality, not throughput. Pay-as-you-go keys allow 30 requests a minute and 4 in flight.
  • Short clips only. Sixty seconds will not show how a model handles a long call. Test a few full recordings over the API.
  • No settings. You cannot set temperature, prompts or response formats. The API exposes the usual OpenAI parameters.
  • A shared key. It is a demo, not a service. Do not build on it.

Questions

Do I need an account to use the playground?

No. BroadNet says the playground needs no sign-up and no card; it calls the live API through a shared key.

Which models does the playground use?

Text and image questions go to Gemma 4. Voice uses the Arabic or the multilingual transcription model, which you pick by language. BroadNet does not list the model behind the documents mode on the page.

How long can a voice clip be?

Up to 60 seconds: a WAV file of up to 4 MB or a WebM recording of up to 1.44 MB. The API itself takes WAV or MP3 files up to 25 MiB.

Is what I upload stored?

BroadNet says request and response content in the playground is not retained, the same zero-data-retention terms as the API. Still, use test files rather than real customer documents.

How do I move from the playground to the API?

Create an account at inference.broadnet.ai to get $5 of free credit with no card, create a key, and send the same request to https://inference.broadnet.ai/v1 with any OpenAI SDK.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity