Text Translation

Organization

sarvamai

text-translation

Write correct Sarvam text translation code (sarvam-translate:v1, mayura:v1) — mode/script/numeral options and silent parameter failures. Use this skill when building text translation or localization features in Python or JS/TS. For whole-document (PDF, Word, Excel) translation, use document-translation instead. For live translate/localize in chat via MCP, use sarvam-mcp instead.

Overview

Publisher	sarvamai
Repository	`skills`
Skill name	`text-translation`
Stars	72
Forks	24
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by sarvamai on GitHub. Read the source before you install it.

Installation

Install the Text Translation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/sarvamai/skills/tree/main/translate/text
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/sarvamai/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/translate/text .claude/skills/text-translation

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Text Translation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Text Translation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Text Translation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Text Translation — Sarvam AI

Live in-chat translate/localize → sarvam-mcp (sarvam_tools_translate / _localize). This skill = SDK code.

Translating whole documents (PDF, DOCX, XLSX, PPTX, HTML)? → document-translation — that is a separate async API, not client.text.translate().

[!IMPORTANT] Auth: api-subscription-key header — NOT Authorization: Bearer. Base URL: https://api.sarvam.ai (NOT /v1 — that prefix is only for the OpenAI-compatible chat endpoint)

Models

Model	Max Input	Languages	Features
`sarvam-translate:v1`	2,000 chars	23 (22 Indian + English)	`mode` (`formal` only), `speaker_gender`, `numerals_format`
`mayura:v1`	1,000 chars	11 (10 Indian + English)	All `mode` values, `output_script`, `speaker_gender`, `numerals_format`, auto source detection

Quick Start (Python)

python
from sarvamai import SarvamAI
client = SarvamAI()

response = client.text.translate(
    input="Hello, how are you?",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="sarvam-translate:v1"
)
print(response.translated_text)

Quick Start (JavaScript/TypeScript)

typescript
import { SarvamAIClient } from "sarvamai";

const client = new SarvamAIClient({ apiSubscriptionKey: "YOUR_SARVAM_API_KEY" });

const response = await client.text.translate({
    input: "Hello, how are you?",
    source_language_code: "en-IN",
    target_language_code: "hi-IN",
    model: "sarvam-translate:v1"
});
console.log(response.translated_text);

Gotchas

Gotcha	Detail
Method name	Both Python & JS: `client.text.translate({...})` — NOT `client.translate.translate()`. Same `text` namespace in both SDKs.
`output_script` on sarvam-translate	NOT supported — only works with `mayura:v1` (`roman`, `fully-native`, `spoken-form-in-native`). Verified live: sending it to `sarvam-translate:v1` now returns `400 invalid_request_error` — `"Transliteration is not supported in sarvam-translate:v1. Please use mayura:v1 for transliteration support or remove the output_script parameter."` — it's a hard error today, not a silent ignore (check your assumptions if you're on an older API/docs snapshot that said otherwise).
`mode` values	`sarvam-translate:v1` supports `formal` only. Colloquial modes (`modern-colloquial`, `classic-colloquial`, `code-mixed`) are `mayura:v1` only. `speaker_gender` works on BOTH models.
Auto language detection	`source_language_code="auto"` only works with `mayura:v1`. `sarvam-translate:v1` requires an explicit source language.
Odia language code	`od-IN` — NOT `or-IN`.
Character limits	Exceeding returns 422. Split long text at sentence boundaries.

Full Docs

Fetch language codes, mode examples, script options, and numeral formats from:

https://docs.sarvam.ai/llms.txt — comprehensive docs index
Translation Guide
Rate Limits

Frequently asked questions

What does the Text Translation AI skill do?

Why use Text Translation on TypingMind?

Because you install it once and use it with any model. Text Translation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Text Translation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sarvamai/skills/tree/main/translate/text. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Text Translation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Text Translation?

As many as you like. As long as a model supports skills, you can use Text Translation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Text Translation AI skill free?

Yes. It is published on GitHub by sarvamai under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Gitcrawl

openclaw

OrganizationPopular

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Graincrawl

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Text Translation — Sarvam AI

Models

Quick Start (Python)

Quick Start (JavaScript/TypeScript)

Gotchas

Full Docs

Frequently asked questions

Related AI Skills

Set up your own AI workspace now