sarvam-mcp

Given an audio file of a call between two parties and a list of questions, This API analyzes the content and returns the transcript, along with responses to the questions. Each response is supported by reasoning and exact phrases extracted from the transcript. ⚠️ Important: Please use Batch API Notebook for call recordings more than 30 seconds. Duration Guidelines: Files under 30 seconds: Use this direct API endpoint Files over 30 seconds: Use our Batch API (required) Resources: Interactive Demo: Try Call Analytics Playground Batch API Documentation: View Notebook Headers api-subscription-key string Required Request This endpoint expects a multipart form containing a file. file file Required The audio file to be analyzed. Must be passed as a form input if using multipart/form-data. Supported formats are WAV (.wav) and MP3 (.mp3). Optimal sample rate is 16kHz. Multi-channel audio will be merged to mono. File size must be less than 10MB and audio duration must not exceed 600 seconds (10 minutes). questions string Required List of questions to be answered based on the call content. Each question should be a valid JSON object with the following structure: {id: string, text: string, description: string (optional), type: string, properties: object}. The type field must be one of: boolean, enum, short answer, long answer, or number. For enum type questions, include an ‘options’ list in the properties. hotwords string Optional Optional comma-separated string of keywords specific to your domain. These keywords will be preserved as-is in the transcript. model enum Optional Model to be used for converting speech to text in target language Allowed values: saaras:v1 saaras:v2 saaras:turbo saaras:flash Response Successful Response transcript string Full transcript of the call generated by Sarvam’s inhouse speech-to-text model. request_id string Optional file_name string Optional Unique identifier for the analyzed audio file. answers list of objects Optional List of answers to predefined questions, derived from the call analysis. It can be null if no valid answers were generated. Show 5 properties duration_in_seconds double Optional Duration of the analyzed call in seconds. language_code enum Optional This will return the BCP-47 code of language spoken in the input. If multiple languages are detected, this will return language code of most predominant spoken language. If no language is detected, this will be null Show 11 enum values diarized_transcript object Optional Diarized transcript of the provided speech Show 1 properties Errors 400 Analytics Call Request Bad Request Error 403 Analytics Call Request Forbidden Error 422 Analytics Call Request Unprocessable Entity Error 429 Analytics Call Request Too Many Requests Error 500 Analytics Call Request Internal Server Error 503 Analytics Call Request Service Unavailable Error POST /call-analytics curl -X POST https://api.sarvam.ai/call-analytics \ -H "api-subscription-key: <apiSubscriptionKey>" \ -H "Content-Type: multipart/form-data" \ -F file=@<file1> \ -F questions="questions" { "transcript": "Agent: Thank you for calling customer support. How may I assist you today?\nCustomer: Hi, I'm having issues with my internet connection. It keeps cutting out.\nAgent: I'm sorry to hear that. Let's troubleshoot this issue...", "request_id": "request_id", "file_name": "call_20230901_123456.mp3", "answers": [ { "id": "q001", "question": "What was the main issue discussed in the call?", "reasoning": "The customer repeatedly mentioned issues with their internet connection.", "response": "INTERNET_ISSUES", "utterance": "My internet keeps cutting out every few minutes. It's really frustrating." } ], "duration_in_seconds": 180.5, "language_code": "hi-IN", "diarized_transcript": { "entries": [ { "transcript": "transcript", "start_time_seconds": 1.1, "end_time_seconds": 1.1, "speaker_id": "speaker_id" } ] } }