Transcript speech to text

Help me Build my Workflow
1

Hi Everyone , I need your help for a transcript voice to text

I building telegram assistant for free , Does anyone know how to transcript speech to text for free

Thanks.

1 Like
2

Hey @Muhammed_Emad, while you wait for a response, here are some things that might help:

Suggested resources

Automatically matched to your question.

Docs:

Forum:

@solomon - you’ve helped with similar issues before, can you take a look?

Automatically suggested by n8n’s community bot. It’s a pilot - please share feedback here.

3

There is no completely free way?

1 Like
4

Unless you find a free api or self host, most likely, no, but, if youy were to setup a localhosted tts model, put it on a public endpoint, you could use it on cloud.

1 Like
5

Hey @Muhammed_Emad Welcome to the communityy

Yes, two ways, and both stay inside n8n.

The Google Gemini node has an Audio operation called Transcribe a Recording, and a Gemini API key from Google AI Studio costs nothing. Wire it as Telegram Trigger, then a Telegram node set to File, Get, with Download switched on, then the Gemini node with Input Type set to binary. It uploads the voice note and returns the text, and the free tier covers the Flash models. One thing to know: on the free tier Google says your content is used to improve their products.
I havent used this one myself so cant be sure of the accuracy but since it’s google i’m kinda sure it’ll good.

If you’d rather have Whisper, Groq’s free plan runs “whisper-large-v3-turbo” at roughly eight hours of audio a day. Add an OpenAI credential in n8n with the Base URL changed to https://api.groq.com/openai/v1 and use the OpenAI node’s Transcribe a Recording.

Check this out if it helps :slight_smile:

2 Likes
6

oh yea! I forgot abt gemini’s free tier!

2 Likes
7

For a Telegram assistant, I would keep the flow simple: use a Telegram trigger, download the voice file, send it to a transcription step, then return the text to the chat. That avoids building a custom speech model and makes it easier to debug when a file format changes. For quick testing outside the workflow, Speech to Text is a handy way to check how an audio clip converts before you wire it into automation. Once the transcript looks clean, you can pass it on to summarising or saving it in your notes app. Just watch the audio length and format in your first tests, since those are the usual reasons a transcription step fails.