菜单
Translate text between English and Indian languages using Sarvam AI (Sarvam-Translate, Mayura). Handles content translation and app localization across 22+ languages with mode control, script options, and numeral formats. Use when translating or localizing content for Indian users.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Chat completions using Sarvam AI LLMs (Sarvam-105B, Sarvam-30B). Handles AI chat, text generation, reasoning, coding, and multilingual conversations in Indian languages. OpenAI-compatible API. Use when building chatbots, Q&A systems, agents, or any LLM feature targeting Indian users.
Transcribe audio to text using Sarvam AI's Saaras model. Handles speech recognition, transcription, and voice interfaces for 23 Indian languages. Supports 5 output modes, auto language detection, WebSocket streaming, and batch diarization. Use when converting speech to text or building voice-enabled apps.
Convert text to natural speech using Sarvam AI's Bulbul v3 model. Handles audio generation, voiceovers, and voice interfaces for 11 Indian languages with 30+ voices. Supports REST, HTTP streaming, WebSocket, and pronunciation dictionaries. Use when generating spoken audio from text.
Build conversational voice agents using Sarvam AI with LiveKit or Pipecat. Handles voice assistants, phone bots, IVR, and real-time conversational AI for Indian languages. Integrates Sarvam STT (Saaras v3), TTS (Bulbul v3), and LLM (Sarvam-30B) with low-latency streaming. Use when creating voice-enabled applications or real-time speech pipelines.
| name | translate |
| description | Translate text between English and Indian languages using Sarvam AI (Sarvam-Translate, Mayura). Handles content translation and app localization across 22+ languages with mode control, script options, and numeral formats. Use when translating or localizing content for Indian users. |
| license | Apache-2.0 |
| metadata | {"author":"sarvam-ai","version":"3.0"} |
[!IMPORTANT] Auth:
api-subscription-keyheader — NOTAuthorization: Bearer. Base URL:https://api.sarvam.ai/v1
| Model | Max Input | Languages | Features |
|---|---|---|---|
sarvam-translate:v1 | 2,000 chars | 22 languages | Formal style, numerals_format |
mayura:v1 | 1,000 chars | 11 languages | mode, output_script, speaker_gender |
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)
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);
| 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. Silently ignored on sarvam-translate:v1. |
mode/speaker_gender | Only work with mayura:v1. sarvam-translate:v1 only supports formal style + numerals_format. |
| Odia language code | od-IN — NOT or-IN. |
| Character limits | Exceeding returns 422. Split long text at sentence boundaries. |
Fetch language codes, mode examples, script options, and numeral formats from: