The moment it happens

Turn voice notes into text with a reply

Send your bot a voice note and get the transcript back with a short answer.

Runs: The moment it happens
Apps: Telegram
AI: Yes, uses the built-in AI allowance
Access: bot token

Send this to your assistant

Create a ClickRuntime automation: when I send a voice message to my Telegram bot, transcribe it with my OpenAI key and reply with the text and a short answer.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

People who think out loud record voice notes for ideas, meeting recaps or questions, then never listen to them again. Replaying a three-minute note is slower than reading it, and searching a pile of audio for one detail is impossible. The idea captured on a walk stays locked in a file nobody opens.

When you send a voice note to your Telegram bot, ClickRuntime fetches the audio with getFile, transcribes it with your own OpenAI Whisper key and asks ClickRuntime's built-in AI to reply to what you said, whether that is a question or a request to clean up your notes. You receive both the transcript and the answer in the chat.

It suits busy people who talk faster than they type, such as drivers, parents and people on a commute.

What you get out of it

Spoken ideas become searchable text
Once the note is transcribed, you can search it in Telegram like any message. Finding what you said last Tuesday takes seconds instead of replaying files. Even a long ramble becomes a block of text you can scan, copy and send on to somebody else.
Speaking is faster than typing
Most people talk several times faster than they type on a phone. Capturing a long thought by voice saves time and keeps you from shortening it. Short notes recorded in a minute can hold what would take ten minutes to type.
You get an answer, not only a transcript
The AI replies to the content, answering a question or tidying rambling notes into a short list. The note becomes useful immediately. Questions get real answers, and a messy list of thoughts comes back as something you can use.
It works when your hands are busy
Walking, driving with a hands-free setup or cooking all leave your voice free. You capture ideas at the moment they appear. Ideas rarely arrive at a desk, and a hands-free route keeps them from being lost on the way.
Accuracy comes from Whisper
A well-known speech model handles accents and many languages. Using your own key means cost stays on your own account. Billing on your own account keeps the cost visible and entirely under your own control.

How it works

What happens, step by step

When you send a voice note to your Telegram bot, ClickRuntime downloads the audio straight away.
It turns the audio into text using your own OpenAI speech-to-text account.
AI writes a reply to what you said.
The bot sends back the transcript and the reply.

Before it runs live

Connect Telegram
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Turn voice notes into text with a replyjust nowSucceeded

Telegram · Voice notesYou said: what time does the Northwind office open on Saturdays They usually open at 10am on Saturdays.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Slack
Combine it with other Telegram steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

voice_notes_transcribed_and_answered.pyexample

from clickruntime import on_event, http, credentials, ai

def tg(method, **params):
    r = http.post(f"https://api.telegram.org/bot{credentials.secret('TELEGRAM_BOT_TOKEN')}/{method}", json=params)
    r.raise_for_status()
    return r.json()["result"]

@on_event
def handle(event):
    msg = (event.json or {}).get("message") or {}
    if "voice" not in msg:
        return {"replied": False}
    token = credentials.secret("TELEGRAM_BOT_TOKEN")
    path = tg("getFile", file_id=msg["voice"]["file_id"])["file_path"]
    audio = http.get(f"https://api.telegram.org/file/bot{token}/{path}").content
    text = http.post("https://api.openai.com/v1/audio/transcriptions",
                     headers={"Authorization": f"Bearer {credentials.secret('OPENAI_API_KEY')}"},
                     data={"model": "whisper-1"}, files={"file": ("voice.ogg", audio)}).json()["text"]
    answer = ai.generate(text, system="Reply with a short, helpful answer.", max_output_tokens=200).text
    tg("sendMessage", chat_id=msg["chat"]["id"], text=f"You said: {text}\n\n{answer}")
    return {"chars": len(text)}

FAQ

Common questions

Why do I need my own OpenAI key?

Speech transcription uses Whisper, which is billed through your OpenAI account. The key is stored as a secret. The reply that follows uses ClickRuntime's built-in AI, so no second key is required. It remains billed on your own account.

How long can a voice note be?

Telegram voice notes and the transcription service have size limits, and very long recordings may need to be split. Short notes of a few minutes work well and return within seconds. Splitting a recording is simple.

Can the transcript be sent to my email as well?

Yes. Along with replying in the chat, the transcript can be emailed or saved to state for a weekly digest. Tell your assistant where you want copies and approve the change. Copies cost nothing extra.

What permissions does it need?

bot token. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly AI allowance.

How many runs does it use?

One run for each event the app sends.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happensAI