---
title: "Voice notes to text for business - WhatsApp and Telegram"
description: "Turn customer voice notes from WhatsApp Business and Telegram bots into transcripts and support tickets: download, transcribe, extract fields with an LLM, route."
url: https://broadrouter.com/blog/voice-notes-to-text-for-business/
lang: en
updated: 2026-11-14
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Voice notes to text for business: WhatsApp and Telegram to tickets

By the BroadNet Inference team · 4 min read · Published 2026-11-14 · Updated 2026-11-16

To turn customer voice notes into tickets, download each note from the WhatsApp Cloud API or Telegram Bot API as soon as the webhook arrives, convert it to WAV, transcribe it with the right language code, then ask an LLM to extract intent, urgency and order numbers as JSON. Create the ticket with the transcript attached and reply in text.

## Key takeaways

-   Download fast: WhatsApp media URLs expire after 5 minutes and webhook media IDs after 7 days.
-   Telegram bots can download files up to 20 MB, through a link valid for at least an hour.
-   Transcription is the cheap step: 10,000 Arabic voice notes of 30 seconds cost $21.00.
-   An LLM turns a rambling note into ticket fields: intent, urgency, order number, language and a one-line summary.
-   Keep the transcript, not the audio, unless you have a reason to store voice.

**On this page**

1.  How does a voice note become a support ticket?
2.  Steps 1 and 2: how do you get the audio out of WhatsApp?
3.  How do you get voice notes out of a Telegram bot?
4.  Step 5: how do you turn a transcript into a ticket?
5.  Which edge cases should you handle early?
6.  What a team gets from it
7.  What does voice-note transcription cost?
8.  How should you handle privacy and retention?
9.  Where BroadNet Inference fits

_[image: An invoice, a phone showing an audio waveform and the Arabic word "مرحبا", with the text "Speech. Documents. Intelligence."]_

In much of the Middle East, customers do not type. They send a 40-second voice note in Gulf or Egyptian Arabic, often with an order number read out in the middle. Agents then listen, rewind, and type it into the helpdesk. Multiply by a few hundred a day and voice notes become the slowest channel you have.

This post builds the business workflow around transcription: getting notes out of WhatsApp and Telegram, turning them into structured tickets, and keeping the data under control. For the conversion and transcription code itself, see our step-by-step guide to [transcribing WhatsApp voice notes](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/). We will not repeat it here.

## How does a voice note become a support ticket?

1.  **Receive** the webhook from WhatsApp or Telegram.
2.  **Download** the audio immediately.
3.  **Convert** to 16 kHz mono WAV.
4.  **Transcribe** with the right language code.
5.  **Extract** ticket fields with an LLM.
6.  **Create** the ticket, with transcript, and reply in text.
7.  **Delete** the audio file.

## Steps 1 and 2: how do you get the audio out of WhatsApp?

On the WhatsApp Business Cloud API, an inbound voice note arrives as a webhook with a media ID, not the file. Meta’s [media docs](https://developers.facebook.com/documentation/business-messaging/whatsapp/business-phone-numbers/media) set the rules:

-   Call `GET /<MEDIA_ID>` on the Graph API to get a `url`.
-   Download that URL with `Authorization: Bearer <token>`. Without the token the request fails.
-   “Media URLs expire after 5 minutes.” Request a new one if you are late.
-   Media IDs from incoming webhooks are valid for **7 days**.

```python
import os, requests

GRAPH = os.environ["GRAPH_BASE"]          # e.g. https://graph.facebook.com/<version>
HDR = {"Authorization": f"Bearer {os.environ['WA_TOKEN']}"}

def download_whatsapp(media_id, path):
    url = requests.get(f"{GRAPH}/{media_id}", headers=HDR, timeout=10).json()["url"]
    with open(path, "wb") as f:
        f.write(requests.get(url, headers=HDR, timeout=30).content)
```

Do this in the webhook handler’s background job, not later in a batch. A queue that runs once an hour will hit expired URLs.

## How do you get voice notes out of a Telegram bot?

A Telegram bot receives a `voice` object with a `file_id`. The [Bot API](https://core.telegram.org/bots/api#getfile) says bots “can download files of up to 20MB”, via `https://api.telegram.org/file/bot<token>/<file_path>`, and the link is “valid for at least 1 hour”.

```python
TG = f"https://api.telegram.org/bot{os.environ['TG_TOKEN']}"

def download_telegram(file_id, path):
    file_path = requests.get(f"{TG}/getFile", params={"file_id": file_id}, timeout=10).json()["result"]["file_path"]
    with open(path, "wb") as f:
        f.write(requests.get(f"https://api.telegram.org/file/bot{os.environ['TG_TOKEN']}/{file_path}", timeout=30).content)
```

Both platforms deliver Ogg/Opus voice notes in practice. The transcription endpoint takes WAV or MP3, so convert with the one-line ffmpeg command from the [WhatsApp guide](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/), then transcribe with `language="ar"` (or the customer’s language).

## Step 5: how do you turn a transcript into a ticket?

A raw transcript is still hard to triage. An LLM can pull out the fields your helpdesk needs:

```python
import json
from openai import OpenAI

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

FIELDS = ("Return JSON with: intent (refund|delivery|billing|technical|other), urgency (low|normal|high), "
          "order_number (string or null), language, summary_en (one sentence), needs_human (true/false).")

def to_ticket(transcript):
    reply = client.chat.completions.create(
        model="broadnet/qwen3.8-27b",
        response_format={"type": "json_object"},
        messages=[{"role": "system", "content": "You triage customer support voice notes. " + FIELDS},
                  {"role": "user", "content": transcript}],
    ).choices[0].message.content
    return json.loads(reply)
```

[Qwen3.8 27B](https://broadrouter.com/models/qwen3.8-27b/) is the model BroadNet tested for Arabic, including Gulf and Egyptian dialects. Validate the JSON before you write it to the helpdesk, and fall back to `needs_human: true` when parsing fails; the [structured output post](https://broadrouter.com/blog/structured-output-json-schema/) has a validate-and-repair loop. If a note mentions card or ID numbers, redact before this step; see [sending sensitive data to an LLM API](https://broadrouter.com/blog/llm-api-sensitive-data/).

## Which edge cases should you handle early?

Real inboxes are messier than a demo. Plan for these from the first week:

-   **Several notes in a row.** Customers often send three short notes instead of one long one. Group notes from the same sender within a couple of minutes into one ticket, and transcribe them in order.
-   **Very short notes.** “Okay” or “thanks” notes do not need a ticket. Skip extraction when the transcript is under a few words.
-   **Forwarded notes.** A forwarded voice note may be someone else speaking. Treat it as an attachment, not as the customer’s own words.
-   **Mixed language.** Gulf customers mix in English product names. If your queue serves several languages, record the language you sent with each transcript so agents know what to expect.
-   **Large files.** Meta’s media docs list a 16 MB audio limit and Telegram bots can download up to 20 MB, both under the 25 MiB transcription limit, but long recordings still take longer. Process them in the background.

## What a team gets from it

| Before | After |
| --- | --- |
| Agent listens to each note, often twice | Agent reads a transcript and a one-line summary |
| Notes cannot be searched | Transcripts are searchable by order number or keyword |
| Triage by whoever is free | Routing by intent and urgency |
| Arabic notes wait for an Arabic speaker | English summary lets any agent pick up simple cases |

## What does voice-note transcription cost?

Transcription is the cheap part of the pipeline. At $0.0042 a minute, 10,000 Arabic voice notes of 30 seconds cost $21.00. The 14-language model costs $0.002 a minute. The LLM step is priced per token; a short transcript plus the instruction is typically a few hundred tokens. Put your own volumes into the [speech-to-text cost calculator](https://broadrouter.com/tools/speech-to-text-cost-calculator/), or compare other providers in the [speech-to-text pricing comparison](https://broadrouter.com/blog/speech-to-text-api-pricing-compared/).

## How should you handle privacy and retention?

Voice notes are personal data, and they often contain more than the customer meant to share. Three habits help:

-   **Delete audio after transcription** unless a policy requires you to keep it.
-   **Store transcripts with the ticket**, under the helpdesk’s access controls, not in app logs.
-   **Use a provider that does not keep audio.** BroadNet keeps no audio or transcripts after the request; see [zero data retention](https://broadrouter.com/zero-data-retention/).

Reply in plain text, and keep first replies to new contacts short and free of links. Messaging platforms watch for spam-like patterns from business numbers.

## Where BroadNet Inference fits

BroadNet covers the transcription and extraction steps with one OpenAI-compatible key: [BroadNet Transcribe Arabic](https://broadrouter.com/models/cohere-transcribe-arabic/) for Arabic notes, BroadNet Transcribe for Arabic plus 13 other languages, and Arabic-tested chat models for the ticket fields. BroadNet reports its Arabic model #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. The $5 starting credit covers about 1,190 minutes of Arabic audio.

BroadNet does not connect to WhatsApp, Telegram or your helpdesk for you; the webhook handling and ticket creation are your code or your automation tool. Calls are a different shape of problem, with two speakers and long recordings: see [transcribing call center recordings](https://broadrouter.com/blog/transcribe-call-center-recordings/).

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.

[Token](https://broadrouter.com/glossary/token/)

A token is the unit of text a language model reads and writes: a word, part of a word, a punctuation mark or a byte sequence produced by the model's tokenizer. LLM APIs count, limit and usually bill usage in tokens.

[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.

[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.

[Dialectal Arabic](https://broadrouter.com/glossary/dialectal-arabic/)

Dialectal Arabic is the everyday spoken Arabic of a region or city, such as Egyptian, Gulf, Levantine or Maghrebi Arabic. Dialects differ from Modern Standard Arabic in sounds, words and grammar, have no standard spelling, and are increasingly written online, which makes them harder for language models.

[Structured output](https://broadrouter.com/glossary/structured-output/)

Structured output is an LLM API feature that constrains a model's reply to a format the developer specifies, usually a JSON Schema, so code can parse it reliably. It is stricter than JSON mode, which guarantees valid JSON but not a particular shape.

[Tool calling](https://broadrouter.com/glossary/tool-calling/)

Tool calling, also called function calling, is an LLM API feature in which the model returns a structured request to run a function the developer has defined, with JSON arguments. The application runs the function and sends the result back; the model never runs code itself.

[Zero data retention](https://broadrouter.com/glossary/zero-data-retention/)

Zero data retention (ZDR) is a data-handling policy in which an AI provider processes prompts and outputs only to serve a request and does not store that content afterward, in logs, caches or training data. Content-free records such as token counts and timings are usually still kept.

## Questions

### Can I transcribe WhatsApp voice notes automatically?

Yes. With the WhatsApp Business Cloud API, each voice note arrives as a webhook with a media ID. Your server fetches the media URL, downloads the file with your access token, converts it and sends it to a transcription API.

### How do I convert Telegram voice messages to text?

Your bot receives a voice object with a file\_id. Call getFile, download the file from the returned path, convert it to WAV with ffmpeg and transcribe it. Bots can download files up to 20 MB.

### How much does it cost to transcribe customer voice notes?

With BroadNet Transcribe Arabic at $0.0042 a minute, 10,000 notes of 30 seconds cost $21.00. The 14-language model costs $0.002 a minute.

### Should I reply to a voice note with a voice note?

Usually a short text reply works better for support: the customer can read it anywhere and it is searchable on both sides. Keep the first reply plain and short.

### Do I need to store the original audio?

Often not. The transcript is enough for most support workflows. If you keep audio for quality or legal reasons, set a retention period and restrict access, because voice is personal data.

## Keep reading

-   [Arabic meeting minutes from recordings: an API pipeline](https://broadrouter.com/blog/arabic-meeting-minutes-from-recordings/)
-   [Arabic speech-to-text API: how to choose one in 2026](https://broadrouter.com/blog/arabic-speech-to-text-api-buyers-guide/)
-   [How to transcribe call center recordings: an Arabic-ready pipeline](https://broadrouter.com/blog/transcribe-call-center-recordings/)
-   [Speech-to-text API pricing compared: price per minute in 2026](https://broadrouter.com/blog/speech-to-text-api-pricing-compared/)
-   [Sending sensitive data to an LLM API: redact, minimise, log less](https://broadrouter.com/blog/llm-api-sensitive-data/)
-   [Record audio in the browser and send it to a speech-to-text API](https://broadrouter.com/blog/record-browser-audio-transcription-api/)
-   [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: Transcribe WhatsApp voice notes to text with an API](https://broadrouter.com/guides/transcribe-whatsapp-voice-notes/)
-   [Guide: Arabic speech-to-text API, step by step](https://broadrouter.com/guides/arabic-speech-to-text-api/)

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-voice-notes-to-text-for-business&utm_content=page-cta) ·

**Sources**

-   [Meta WhatsApp Cloud API, media (retrieve and download; fetched 2026-11-14)](https://developers.facebook.com/documentation/business-messaging/whatsapp/business-phone-numbers/media)
-   [Telegram Bot API, getFile and Voice (fetched 2026-11-14)](https://core.telegram.org/bots/api#getfile)
-   [BroadNet Inference API reference, transcription](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-voice-notes-to-text-for-business&utm_content=sources)
-   [BroadNet Inference machine-readable prices (pricing.json)](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=blog-voice-notes-to-text-for-business&utm_content=sources)
