*** title: "\U0001F44B Welcome to Sarvam AI Docs" layout: overview description: >- Welcome to Sarvam AI documentation. Access comprehensive guides, API references, quickstart tutorials, and community resources for Indian language AI development. canonical-url: '[https://docs.sarvam.ai/api-reference-docs/overview](https://docs.sarvam.ai/api-reference-docs/overview)' 'og:title': Sarvam AI Documentation - Indian Language AI Platform 'og:description': >- Comprehensive documentation for Sarvam AI's Indian language processing APIs. Get started with guides, tutorials, and API references for chat, speech, and text processing. 'og:type': website 'og:site\_name': Sarvam AI Developer Documentation 'og:image': type: url value: >- [https://res.cloudinary.com/dvcb20x9a/image/upload/v1743510800/image\_3\_rpnrug.png](https://res.cloudinary.com/dvcb20x9a/image/upload/v1743510800/image_3_rpnrug.png) 'og:image:width': 1200 'og:image:height': 630 'twitter:card': summary\_large\_image 'twitter:title': Sarvam AI Documentation - Indian Language AI Platform 'twitter:description': >- Comprehensive documentation for Sarvam AI's Indian language processing APIs. Get started with guides, tutorials, and API references for chat, speech, and text processing. 'twitter:image': type: url value: >- [https://res.cloudinary.com/dvcb20x9a/image/upload/v1743510800/image\_3\_rpnrug.png](https://res.cloudinary.com/dvcb20x9a/image/upload/v1743510800/image_3_rpnrug.png) 'twitter:site': '@SarvamAI' --------------------------- Get your API key and make your first request in under 5 minutes. Complete setup guide with authentication and code examples. {" "} Explore Sarvam AI's specialized models for Indian languages - from speech processing to text generation and translation. {" "} Join our developer community for support, discussions, and updates. Connect with other developers building with Sarvam AI. {" "} Step-by-step tutorials and code examples for building applications with Sarvam AI APIs. From basic usage to advanced implementations. ## Docs - [Developer Quickstart](https://docs.sarvam.ai/api-reference-docs/getting-started/quickstart.mdx): Learn how to make your first API request with Sarvam AI in under 5 minutes. Complete guide with code examples for chat completion, speech-to-text, and translation APIs. - [Libraries & SDKs](https://docs.sarvam.ai/api-reference-docs/getting-started/sd-ks-libraries.mdx): Official client libraries for Python and JavaScript to integrate Sarvam AI APIs. - [Models](https://docs.sarvam.ai/api-reference-docs/getting-started/models.mdx): Complete overview of Sarvam AI's specialized models for Indian languages. Choose the right model for your use case - from speech processing to text generation, translation, and document intelligence. - [Saaras](https://docs.sarvam.ai/api-reference-docs/getting-started/models/saaras.mdx): Saaras v3 - Domain-aware speech translation model that converts speech directly to English text with enhanced telephony support and intelligent entity preservation. - [Bulbul](https://docs.sarvam.ai/api-reference-docs/getting-started/models/bulbul.mdx): Bulbul v3 - High-quality multilingual text-to-speech model for Indian languages with natural prosody and 30+ speaker voices. - [Mayura](https://docs.sarvam.ai/api-reference-docs/getting-started/models/mayura.mdx): Mayura - Advanced multilingual translation model for Indian languages with customizable translation styles, script control, and intelligent code-mixed content handling. - [Sarvam Translate](https://docs.sarvam.ai/api-reference-docs/getting-started/models/sarvam-translate.mdx): Sarvam Translate - Comprehensive translation model supporting all 22 official Indian languages with formal translation style and structured text optimization. - [Sarvam-30B](https://docs.sarvam.ai/api-reference-docs/getting-started/models/sarvam-30b.mdx): Sarvam-30B - 30B parameter multilingual language model optimized for Indian languages with strong reasoning, coding, and conversational capabilities. - [Sarvam-105B](https://docs.sarvam.ai/api-reference-docs/getting-started/models/sarvam-105b.mdx): Sarvam-105B - 105B parameter flagship multilingual language model delivering state-of-the-art performance on Indian language understanding, reasoning, and generation tasks. - [Sarvam Vision](https://docs.sarvam.ai/api-reference-docs/getting-started/models/sarvam-vision.mdx): Sarvam Vision - A 3B parameter multimodal model delivering world-class Document Intelligence and visual understanding with unmatched accuracy for 23 languages (22 Indian + English). - [Sarvam-M (Legacy)](https://docs.sarvam.ai/api-reference-docs/getting-started/models/sarvam-m.mdx): Sarvam-M - 24B parameter multilingual, hybrid-reasoning language model with 20% improvement on Indian language benchmarks and Wikipedia grounding support. - [Saarika](https://docs.sarvam.ai/api-reference-docs/getting-started/models/saarika.mdx): Saarika v2.5 - High-accuracy speech recognition model for Indian languages with superior multi-speaker handling, telephony optimization, and automatic code-mixing support. - [Credits & Rate Limits](https://docs.sarvam.ai/api-reference-docs/ratelimits.mdx): Understand Sarvam AI rate limits by plan tier, per-API concurrency limits, and how to handle 429 and 503 errors gracefully. View your current limits on the dashboard. - [Talk to us](https://docs.sarvam.ai/api-reference-docs/help.mdx): Get help and support for Sarvam AI APIs. Contact our team via Discord or email for technical questions, bug reports, feature requests, and enterprise inquiries. - [Pricing](https://docs.sarvam.ai/api-reference-docs/pricing.mdx): Transparent pricing for all Sarvam AI services. View rates for chat completion, speech-to-text, text-to-speech, translation, and other Indian language AI APIs in Indian Rupees. - [Change Log](https://docs.sarvam.ai/api-reference-docs/changelog.mdx): Stay updated with the latest Sarvam AI API changes, new features, and improvements. Track releases for speech-to-text, translation, chat completion, and other services. - [Chat Completions Overview](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/overview.mdx): Get started with Sarvam AI LLM models for conversational AI. Build intelligent chat applications with native Indian language support and deep contextual reasoning capabilities. - [How to list your chat messages](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/list-your-chat-messages.mdx): Defines your entire conversation. - [How to control response randomness with `temperature`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/control-response-randomness.mdx): Controls how random or deterministic the model's responses will be. - [How to control response diversity with `top_p`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/control-response-diversity.mdx): Method used to generate text by limiting the possibilities of the next word - [How to adjust the model's thinking level with `reasoning_effort`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/adjust-the-models-thinking-level.mdx): controls **how much effort the model puts into reasoning. - [How to improve factual accuracy with `wiki_grounding`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/improve-response-factual-accuracy.mdx): Model uses a RAG based approach to retrieve relevant chunks from Wikipedia. - [How to encourage new topics with `presence_penalty`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/encourage-new-topics-in-response.mdx): Helps you steer the model toward introducing new concepts or topics. - [How to reduce repetition with `frequency_penalty`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/reduce-repetition-words-or-phrases-in-response.mdx): Helps you control how often the model repeats words or phrases - [How to get repeatable results using `seed`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/get-repeatable-results.mdx): Get the same output every time for the same prompt - [How to control the response length with `max_tokens`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/control-the-response-length.mdx): control how long the model's response can be - [How to control where the model stops using `stop`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/chat-completion/how-to/control-where-the-model-stops.mdx): Tell the model to **stop generating further tokens. - [Speech-to-Text APIs](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/overview.mdx): Complete overview of Sarvam AI Speech-to-Text APIs including real-time, batch, and streaming options. Process audio with Saarika and Saaras models for high-accuracy transcription. - [Speech-to-Text Rest API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/rest-api.mdx): Process short audio files synchronously with immediate response. Instant transcription and translation for quick audio processing with multiple format support. - [Batch Speech-to-Text API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/batch-api.mdx): Process large audio files using synchronous or asynchronous methods. Handle up to 1-hour recordings with speaker diarization, timestamps, and advanced transcription features. - [Streaming Speech-to-Text API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/streaming-api.mdx): Real-time audio transcription and translation with WebSocket connections. Low-latency streaming for live applications with instant results and interactive features. - [How to select output mode](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/how-to/select-output-mode.mdx): Choose the right output mode for your speech-to-text use case with Saaras v3. - [How to specify language codes](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/how-to/specify-language-codes.mdx): Use BCP-47 language codes for accurate speech-to-text transcription with Saaras v3. - [How to enable speaker diarization](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/speech-to-text/how-to/enable-speaker-diarization.mdx): Identify and distinguish between multiple speakers in audio using the Batch API. - [FAQs](https://docs.sarvam.ai/api-reference-docs/speech-to-text/faq.mdx): Frequently asked questions about Sarvam AI speech-to-text services. Get answers about models, pricing, language support, audio formats, and implementation best practices. - [Text-to-Speech Overview](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/overview.mdx): Complete overview of Sarvam AI Text-to-Speech APIs using Bulbul v3 model. Convert text to natural speech with real-time and streaming options for Indian languages. - [Text-to-Speech Rest API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/rest-api.mdx): Real-time conversion of text into speech using customizable voices. Instant audio generation with multiple voice options and various audio formats for Indian languages. - [HTTP Streaming API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/streaming-api/http-stream.mdx): Stream TTS audio over a single HTTP POST request. No WebSocket setup, no connection management — just POST text and pipe the audio response. - [Streaming Text-to-Speech API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/streaming-api/web-socket.mdx): Real-time conversion of text into speech using WebSocket connections. Efficient streaming for long texts with progressive audio generation and low-latency playback. - [Pronunciation Dictionary](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary.mdx): Teach Bulbul v3 how to say specific words — brand names, abbreviations, regional terms — exactly the way you want, across all 11 supported languages. - [Best Practices for Writing Text for TTS](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/best-practices.mdx): A guide to writing text that produces natural-sounding speech output with Sarvam AI Bulbul. - [How to Set the Language](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/set-the-language.mdx): Defines the language for text normalization before speech synthesis. - [How to change the speaker voice](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/change-the-speaker-voice.mdx): Learn how to choose specific voices for text-to-speech output using the speaker parameter. Explore Bulbul v3's 30+ natural-sounding voices for different languages and use cases. - [How to adjust the pitch (tone)](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/adjust-the-tone.mdx): Control the tone of the synthesized speech (bulbul:v2 only). - [How to adjust the pace (speed)](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/adjust-the-speed.mdx): Controls the speed at which the speech is delivered. - [How to adjust the loudness (volume)](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/adjust-the-loudness.mdx): Controls the volume level of the generated audio (bulbul:v2 only). - [How to set the sample rate (audio quality)](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/set-the-sample-rate.mdx): Controls the audio quality and size of the generated output. - [How to enable text preprocessing](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/enable-text-preprocessing.mdx): improves pronunciation (bulbul:v2 only). - [How to set the audio format for output using `output_audio_codec`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/set-audio-format-for-output.mdx): Choose the audio format for TTS streaming output. - [How to set `output_audio_bitrate`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/set-bitrate-for-output.mdx): Control the quality and size of the synthesized audio output. - [How to set maximum length for sentence splitting using `max_chunk_length`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/set-maximum-length-for-sentence-splitting.mdx): Control how long each sentence chunk can be when splitting text for streaming TTS. - [How to set buffer size to start processing in Streaming TTS with `min_buffer_size`](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-to-speech/how-to/set-buffer-size-to-start-processing.mdx): Define when the TTS engine should start processing text from the buffer. - [Text Processing Overview](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-processing/overview.mdx): Complete overview of Sarvam AI Text Processing APIs including translation, transliteration, and language identification for 22+ Indian languages using Mayura and Sarvam-Translate models. - [Text Translation API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-processing/translation.mdx): Complete overview of Sarvam AI Text Translation API supporting English to Indian languages and vice versa with multiple translation modes and high accuracy. - [Transliteration API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-processing/transliteration.mdx): Complete overview of Sarvam AI Transliteration API for script conversion between Indian languages. Convert between Roman, Devanagari, and other scripts with high accuracy. - [Language Identification API](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/text-processing/language-detection.mdx): Identifies the language and script of input text, supporting multiple Indian languages. Automatic detection with confidence scores for multilingual text processing. - [Document Intelligence Overview](https://docs.sarvam.ai/api-reference-docs/api-guides-tutorials/document-intelligence/overview.mdx): Transform documents into structured, queryable data with Sarvam's Document Intelligence API. Powered by Sarvam Vision for accurate text extraction and table parsing across 23 languages (22 Indian + English). - [Build Your First Voice Agent using LiveKit](https://docs.sarvam.ai/api-reference-docs/integration/build-voice-agent-with-live-kit.mdx): A beginner-friendly guide to building a real-time voice agent using LiveKit and Sarvam AI. Support for 11 languages (10 Indian + English) with natural voices and multilingual conversations. - [Build Your First Voice Agent using Pipecat](https://docs.sarvam.ai/api-reference-docs/integration/build-voice-agent-with-pipecat.mdx): A beginner-friendly guide to building a real-time voice agent using Pipecat and Sarvam AI. Support for 11 languages (10 Indian + English) with natural voices and multilingual conversations. - [Welcome to Sarvam AI API Reference Documentation](https://docs.sarvam.ai/api-reference-docs/introduction.mdx): Explore Sarvam AI's comprehensive API documentation for chat completion, speech-to-text, text-to-speech, translation, and more across 22+ Indian languages. - [Authentication](https://docs.sarvam.ai/api-reference-docs/authentication.mdx): Learn how to authenticate your Sarvam AI API requests using API subscription keys. Complete guide with examples and best practices for secure API key management. - [Access to Beta APIs](https://docs.sarvam.ai/api-reference-docs/beta-apis.mdx): Get early access to Sarvam AI's upcoming beta features and APIs. Learn how to request whitelisting for your subscription key and try new features before public release. - [Meta Prompt Guide](https://docs.sarvam.ai/api-reference-docs/metaprompt.mdx): Learn how to use Sarvam AI meta-prompts to guide AI models effectively. Complete guide with examples, templates, and best practices for consistent AI behavior. - [Call Analytics Pipeline](https://docs.sarvam.ai/api-reference-docs/cookbook/guides/call-analytics-pipeline.mdx) - [Collection Agent using LiveKit](https://docs.sarvam.ai/api-reference-docs/cookbook/example-voice-agents/collection-agent.mdx): Build a voice-based collection agent for payment reminders and follow-ups using LiveKit and Sarvam AI. Support for 11 languages (10 Indian + English) with natural voices. - [Government Scheme Awareness Agent using LiveKit](https://docs.sarvam.ai/api-reference-docs/cookbook/example-voice-agents/government-scheme-agent.mdx): Build a voice-based agent that helps citizens understand and apply for government schemes using LiveKit and Sarvam AI. Support for 11 languages (10 Indian + English). - [Tutor Agent using Pipecat](https://docs.sarvam.ai/api-reference-docs/cookbook/example-voice-agents/tutor-agent.mdx): Build a voice-based tutor agent that teaches students in multiple Indian languages using Pipecat and Sarvam AI. Perfect for EdTech applications. - [Loan Advisory Agent using Pipecat](https://docs.sarvam.ai/api-reference-docs/cookbook/example-voice-agents/loan-advisory-agent.mdx): Build a voice-based loan advisory agent that helps customers understand loan options using Pipecat and Sarvam AI. Support for 11 languages (10 Indian + English). ## API Docs - Endpoints > Speech to Text [REST](https://docs.sarvam.ai/api-reference-docs/speech-to-text/transcribe.mdx) - Endpoints > Speech to Text [WebSocket](https://docs.sarvam.ai/api-reference-docs/speech-to-text/transcribe/ws.mdx) - Endpoints > Speech to Text [Batch - Initiate Job](https://docs.sarvam.ai/api-reference-docs/speech-to-text/stt/job/initiate.mdx) - Endpoints > Speech to Text [Batch - Upload Files](https://docs.sarvam.ai/api-reference-docs/speech-to-text/stt/job/upload.mdx) - Endpoints > Speech to Text [Batch - Start Job](https://docs.sarvam.ai/api-reference-docs/speech-to-text/stt/job/start.mdx) - Endpoints > Speech to Text [Batch - Get Status](https://docs.sarvam.ai/api-reference-docs/speech-to-text/stt/job/status.mdx) - Endpoints > Speech to Text [Batch - Download Results](https://docs.sarvam.ai/api-reference-docs/speech-to-text/stt/job/download.mdx) - Endpoints > Speech to Text Translate [REST](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/translate.mdx) - Endpoints > Speech to Text Translate [WebSocket](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/translate/ws.mdx) - Endpoints > Speech to Text Translate [Batch - Initiate Job](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/stt-translate/job/initiate.mdx) - Endpoints > Speech to Text Translate [Batch - Upload Files](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/stt-translate/job/upload.mdx) - Endpoints > Speech to Text Translate [Batch - Start Job](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/stt-translate/job/start.mdx) - Endpoints > Speech to Text Translate [Batch - Get Status](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/stt-translate/job/status.mdx) - Endpoints > Speech to Text Translate [Batch - Download Results](https://docs.sarvam.ai/api-reference-docs/speech-to-text-translate/stt-translate/job/download.mdx) - Endpoints > Text to Speech [REST](https://docs.sarvam.ai/api-reference-docs/text-to-speech/convert.mdx) - Endpoints > Text to Speech [REST Stream](https://docs.sarvam.ai/api-reference-docs/text-to-speech/convert-stream.mdx) - Endpoints > Text to Speech [WebSocket](https://docs.sarvam.ai/api-reference-docs/text-to-speech/stream.mdx) - Endpoints > Pronunciation Dictionary [Create](https://docs.sarvam.ai/api-reference-docs/pronunciation-dictionary/create.mdx) - Endpoints > Pronunciation Dictionary [List](https://docs.sarvam.ai/api-reference-docs/pronunciation-dictionary/list.mdx) - Endpoints > Pronunciation Dictionary [Get](https://docs.sarvam.ai/api-reference-docs/pronunciation-dictionary/get.mdx) - Endpoints > Pronunciation Dictionary [Update](https://docs.sarvam.ai/api-reference-docs/pronunciation-dictionary/update.mdx) - Endpoints > Pronunciation Dictionary [Delete](https://docs.sarvam.ai/api-reference-docs/pronunciation-dictionary/delete.mdx) - Endpoints > Text Processing [Translation](https://docs.sarvam.ai/api-reference-docs/text/translate-text.mdx) - Endpoints > Text Processing [Transliteration](https://docs.sarvam.ai/api-reference-docs/text/transliterate-text.mdx) - Endpoints > Text Processing [Language Detection](https://docs.sarvam.ai/api-reference-docs/text/identify-language.mdx) - Endpoints > Chat Completion [Chat Completion](https://docs.sarvam.ai/api-reference-docs/chat/chat-completions.mdx) - Endpoints > Document Intelligence [Create Document Intelligence Job](https://docs.sarvam.ai/api-reference-docs/document-intelligence/initialise.mdx) - Endpoints > Document Intelligence [Get Document Intelligence Upload URLs](https://docs.sarvam.ai/api-reference-docs/document-intelligence/get-upload-links.mdx) - Endpoints > Document Intelligence [Start Document Intelligence Job](https://docs.sarvam.ai/api-reference-docs/document-intelligence/start.mdx) - Endpoints > Document Intelligence [Get Document Intelligence Job Status](https://docs.sarvam.ai/api-reference-docs/document-intelligence/get-status.mdx) - Endpoints > Document Intelligence [Get Document Intelligence Download URLs](https://docs.sarvam.ai/api-reference-docs/document-intelligence/get-download-links.mdx) ## OpenAPI Specification The raw OpenAPI 3.1 specification for this API is available at: - [OpenAPI JSON](https://docs.sarvam.ai/openapi.json) - [OpenAPI YAML](https://docs.sarvam.ai/openapi.yaml)