> ## Documentation Index > Fetch the complete documentation index at: https://docs.demo.descriptor.ai/llms.txt > Use this file to discover all available pages before exploring further. # Analyze Single File > For the best results, use audio files with a sample rate of 16 kHz and 16 bits per sample. You can start using our API with the command line following these steps: 1. Send a POST request with **audio file link** and **corresponding configuration** in JSON. 2. [Send a GET request to fetch results](/api-reference/get-analysis-result) using the **result\_id** from the response. 3. *Optional*: Configure a **webhook** to receive the results. After configuring the body of the request, please refer to the code snippets rendered dynamically on the right side of the page. ## OpenAPI ````yaml post /api/v1/offline/processing openapi: 3.1.0 info: title: M-Path description: Automatic Speech Recognition and Voice Emotion Recognition version: dev servers: [] security: [] paths: /api/v1/offline/processing: post: tags: - Processing summary: Analyze Single File description: >- For the best results, use audio files with a sample rate of 16 kHz and 16 bits per sample. operationId: analyze_single_file requestBody: content: application/json: schema: $ref: '#/components/schemas/Pipeline' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ResultId' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - HTTPBearer: [] components: schemas: Pipeline: type: object description: Main configuration for audio processing required: - config - audio properties: config: $ref: '#/components/schemas/RecognitionConfig' audio: $ref: '#/components/schemas/RecognitionAudio' call_data: $ref: '#/components/schemas/RecognitionMeta' default: {} example: config: language_code: en-US insights: summary: prompt_customization: Focus on key points and action items sentiment: {} topics: {} audio: uri: https://example.com/audio.wav ResultId: type: object properties: result_id: type: string title: Result ID description: Identifier to retrieve the analysis results HTTPValidationError: type: object properties: detail: type: array items: $ref: '#/components/schemas/ValidationError' RecognitionConfig: type: object description: Configuration for audio processing pipeline properties: language_code: type: string enum: - en-US - he-IL - hi-IN - es-ES - fr-FR - de-DE - it-IT title: Language Code default: en-US description: Primary language of the audio file transcript_model: type: string enum: - openai_whisper title: Transcript Model default: openai_whisper description: Speech-to-text model to use for transcription emotions_model: type: string enum: - emotions - null title: Emotions Model default: emotions description: Model to use for emotion detection. Set to null to disable emotions_alignment: type: boolean title: Emotions Alignment default: false description: Enable temporal alignment of emotions with speech emotions_diarization: type: boolean title: Emotions Diarization default: false description: Enable speaker-based emotion diarization channels: type: integer enum: - 1 - 2 title: Channels default: 2 description: Number of audio channels (1 for mono, 2 for stereo) insights: type: object description: Configure which insights to generate and their options properties: agent_actions: type: object properties: prompt_customization: type: string description: Custom prompt for agent actions analysis default: '' csat: type: object properties: prompt_customization: type: string description: Custom prompt for CSAT analysis default: '' customer_requests: type: object properties: prompt_customization: type: string description: Custom prompt for customer requests analysis default: '' division: type: object properties: prompt_customization: type: string description: Custom prompt for conversation division analysis default: '' keywords: type: object properties: prompt_customization: type: string description: Custom prompt for keywords extraction default: '' label: type: object properties: prompt_customization: type: string description: Custom prompt for labeling default: '' labels: type: array items: type: string description: List of labels to classify the conversation problems: type: object properties: prompt_customization: type: string description: Custom prompt for problems detection default: '' questions: type: object properties: prompt_customization: type: string description: Custom prompt for questions analysis default: '' sentiment: type: object properties: prompt_customization: type: string description: Custom prompt for sentiment analysis default: '' summary: type: object properties: prompt_customization: type: string description: Custom prompt for summary generation default: '' topics: type: object properties: prompt_customization: type: string description: Custom prompt for topics extraction default: '' default: {} webhook: type: string format: uri title: Webhook description: URL to receive processing results when complete nullable: true default: null RecognitionAudio: type: object description: Audio file information required: - uri properties: uri: type: string format: uri title: URI description: Publicly accessible URL to the audio file RecognitionMeta: type: object description: Optional metadata about the call properties: id: type: string title: ID description: Your internal identifier for this call timestamp: type: string format: date-time title: Timestamp description: When the call occurred speakers: type: array items: type: object properties: id: type: string description: Speaker identifier label: type: string description: Display name for the speaker role: type: string enum: - agent - customer description: Role of the speaker required: - id - role description: Information about speakers in the call ValidationError: type: object properties: loc: type: array items: anyOf: - type: string - type: integer msg: type: string type: type: string securitySchemes: HTTPBearer: type: http scheme: bearer ````