Sarvam AI
n8n logo

Sarvam + n8n

Automation

Use the Sarvam community node to add speech to text, text to speech, and chat to any n8n workflow. Transcribe 23 Indian languages plus English, with no backend required. Connect Sarvam to your CRM, support stack, internal tools, or any of the 1,000+ apps n8n supports.

Sarvam APIs supported
saaras:v4

Speech-to-Text

Accurate transcription built for Indian accents, dialects, and real-world audio with speaker diarisation.

bulbul:v4-flash

Text-to-Speech

Natural, expressive voices in 10 Indian languages and English, for conversational agents, dubbing, and accessibility.

sarvam-105b

Language model

Multilingual model with support for Indian languages, for text generation and reasoning.

Sarvam Translate

Translation

High-quality translation across 12+ Indian languages, optimised for conversational and enterprise content.

What you can build

Transcribe audio in 23 Indian languages

Upload audio from a form, pull it from a webhook, or fetch it from storage. Sarvam's speech to text handles Hindi, Tamil, Bengali, Telugu, and 19 more, with modes for standard transcription, code-mixed output, Roman transliteration, or direct translation to English for downstream tools that only read one language.

Synthesize speech that sounds right for Indian users

Turn any text into audio across 11 languages and dozens of speakers. Set the pace, pick the codec, and choose a voice that fits your product. The output goes directly into a Respond to Webhook node, an email, or a storage bucket, wherever your workflow sends audio next.

Run Sarvam's language models on any text

Feed transcripts, form inputs, or scraped content into sarvam-105b for high-quality multilingual reasoning. Chain completions with speech to text and text to speech to build voice Q&A flows, automated call handling, or multilingual support automations, all in the node editor.

A workflow in four nodes

Most Sarvam automations follow the same shape.

1.

Receive audio

A webhook, form, or file download brings audio into the workflow as a binary property.

2.

Transcribe

Sarvam speech to text reads that binary and returns a transcript.

3.

Process

The chat node takes the transcript as a user message and returns a reply.

4.

Respond

Text to speech reads the reply and returns audio you can send, store, or stream back.

No custom backend. No glue code. The node editor wires it.

Popular workflows

Transcribe a form audio upload

A Form Trigger captures the file. Sarvam transcribes it and returns text in JSON. Route it to a CRM, a support ticket, or a Google Sheet.

Form to transcript in seconds
Route to any downstream tool

Webhook voice Q&A

An incoming POST with raw audio goes to Sarvam speech to text, then chat, then text to speech. Respond to Webhook returns the spoken answer. Full round-trip in four nodes.

Full voice round-trip
Four nodes, no backend

Batch transcription from storage

Pull audio files from S3 or Google Drive. Loop through with Sarvam speech to text. Write transcripts to a database or sheet. Useful for call centres, field recordings, or interview archives.

Bulk processing at scale
Call centres and archives

Multilingual support automation

Sarvam's Translate to English mode converts a call in any supported Indian language to English text on transcription. Feed it straight to your existing English-only model or ticketing system. No language detection step, no translation middleware.

No translation middleware
Works with English-only tools

How to install

The Sarvam node is available as a community package on n8n.

Self-hosted? npm install n8n-nodes-sarvam

1.

Open community nodes

Go to Settings, then Community nodes.

2.

Install the package

Search for n8n-nodes-sarvam and install it.

3.

Restart n8n

Restart n8n if prompted.

4.

Add credentials

Go to Credentials, create a new Sarvam AI API credential, and paste your API key from indus.sarvam.ai.

5.

Start building

Add a Sarvam node to any workflow and pick your Resource and Operation.

Quick start
JSON
{
  "resource": "speech",
  "operation": "speechToText",
  "binaryPropertyName": "audio",
  "sttMode": "transcribe",
  "speechToTextOptions": {}
}
Best practices

Match binary field names exactly

Input Binary Field on speech to text must equal the binary field name from the upstream node, such as data or audio. Check the Binary tab instead of guessing.

Name your Sarvam nodes

Rename each node to something like Sarvam STT or Sarvam Chat so $('node name') references survive copy and paste.

Pin sample data while you build

Pin a small audio file on the trigger so you can tune speech to text options without uploading on every run.

Keep keys in credentials

Store the API key in the Sarvam AI API credential, never in expressions or exported workflow JSON. Use n8n external secrets in production.

Use cases

Call

Call transcription pipelines

Transcribe recorded calls and route the transcripts to your CRM, a ticket, or a sheet.

Multilingual

Multilingual support automation

Use translate to English mode so English-only tools can read calls made in any supported Indian language.

Voice

Voice question and answer flows

Chain speech to text, chat, and text to speech behind a webhook and return a spoken answer.

Resources and details
Type Open Source + Cloud
Language No-code (visual)
Maintained by n8n GmbH
Install Self-host or use n8n Cloud

Ready to automate? Follow the n8n guide in the Sarvam docs.