sarvamai/skills
Developer toolsこのページは AI により自動翻訳されています。技術的な詳細は原文をご確認ください。 原文を見る
A curated set of practical skills and examples for building AI applications using Sarvam APIs.
概要
Documentation • Get API Key • Agent Skills Spec LLMs have fixed knowledge from their training cutoff. Sarvam AI's SDK has unique patterns that differ from standard conventions — method names that break expectations (client.text.translate() not client.translate.translate()), parameters that silently fail (output_script on sarvam-translate), and response quirks (content being None when reasoning consumes the token budget). These skills bridge that gap. Each one gives AI coding assistants the exact SDK signatures and gotchas they need to generate correct Sarvam AI code, then routes to llms.txt for detailed documentation. For Sarvam actions (translate this, speak that, dub audio) across Cursor, Claude Code, and other MCP clients, install sarvam-mcp and use the sarvam-mcp skill. The vibe-coding skill is —it is for anyone building with an agent. sarvam-mcp teaches agents to drive the Sarvam MCP server in any harness. The other skills document SDK APIs for writing code.
README
以下は原文 README の抜粋です。原文を見る。
Sarvam AI Skills
Full-stack AI for Bharat
Documentation • Get API Key • Agent Skills Spec
About
LLMs have fixed knowledge from their training cutoff. Sarvam AI’s SDK has unique patterns that differ from standard conventions — method names that break expectations (client.text.translate() not client.translate.translate()), parameters that silently fail (output_script on sarvam-translate), and response quirks (content being None when reasoning consumes the token budget).
These skills bridge that gap. Each one gives AI coding assistants the exact SDK signatures and gotchas they need to generate correct Sarvam AI code, then routes to llms.txt for detailed documentation.
For in-chat Sarvam actions (translate this, speak that, dub audio) across Cursor, Claude Code, and other MCP clients, install sarvam-mcp and use the sarvam-mcp skill.
Skills
The vibe-coding skill is stack- and vendor-agnostic—it is for anyone building with an agent. sarvam-mcp teaches agents to drive the Sarvam MCP server in any harness. The other skills document Sarvam SDK APIs for writing code.
| Skill | Description |
|---|---|
| sarvam-mcp | MCP (any harness) — live sarvam_tools_* vs build-time sarvam_code_*, composites, auth, install, Bulbul v4 Flash in tts_* / voice / dub. Use for in-chat Sarvam actions. |
| chat | SDK — Sarvam-105B/30B completions, streaming, reasoning, content=None gotcha. |
| speech-to-text | SDK — Saaras v3 REST, Batch + diarization, WebSocket streaming. |
| text-to-speech | SDK — Bulbul v4 Flash persona voices, REST/stream/WebSocket, pronunciation dicts, v3/v4 param traps. |
| translate/text | SDK — Mayura / Sarvam-Translate text translation signatures and silent failures. |
| translate/document | SDK — Document Translation API: async create → upload → start → poll → export pipeline for PDF, Word, Excel, PowerPoint, HTML. |
| doc-ai | SDK — Sarvam Vision Document AI: doc_ai.parse()/.extract()/.classify()/.split() — OCR, schema-based field extraction, document classification, and splitting multi-document PDFs. |
| dubbing | SDK — Dubbing API: async create → upload → start → poll pipeline for video/audio localization with voice cloning. |
| voice-agents | SDK — LiveKit / Pipecat real-time voice agents with Bulbul v4 Flash personas. |
推奨ツール
別のキーワードを試すか、フィルタを外してください。
インストール
npx skillfish add sarvamai/skills