> ## Documentation Index > Fetch the complete documentation index at: https://assembly-preview.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Summarize a transcript using LeMUR > Custom Summary allows you to distill a piece of audio into a few impactful sentences. You can give the model context to obtain more targeted results while outputting the results in a variety of formats described in human language. ## OpenAPI ````yaml post /lemur/v3/generate/summary openapi: 3.1.0 info: title: AssemblyAI API description: AssemblyAI API version: 1.3.4 termsOfService: https://www.assemblyai.com/legal/terms-of-service contact: name: API Support email: support@assemblyai.com url: https://www.assemblyai.com/docs/ servers: - url: https://api.assemblyai.com description: AssemblyAI API security: - ApiKey: [] tags: - name: transcript description: Transcript related operations externalDocs: url: https://www.assemblyai.com/docs/guides/transcribing-an-audio-file - name: LeMUR description: LeMUR related operations externalDocs: url: >- https://www.assemblyai.com/docs/guides/processing-audio-with-llms-using-lemur - name: streaming description: Streaming Speech-to-Text externalDocs: url: https://www.assemblyai.com/docs/speech-to-text/streaming paths: /lemur/v3/generate/summary: post: tags: - LeMUR summary: Summarize a transcript using LeMUR description: > Custom Summary allows you to distill a piece of audio into a few impactful sentences. You can give the model context to obtain more targeted results while outputting the results in a variety of formats described in human language. operationId: lemurSummary requestBody: description: Params to generate the summary required: true content: application/json: schema: $ref: '#/components/schemas/LemurSummaryParams' responses: '200': description: LeMUR summary response content: application/json: schema: $ref: '#/components/schemas/LemurSummaryResponse' headers: X-RateLimit-Limit: schema: type: integer description: Maximum number of allowed requests in a 60 second window. X-RateLimit-Remaining: schema: type: integer description: Number of remaining requests in the current time window. X-RateLimit-Reset: schema: type: integer description: >- Number of seconds until the remaining requests resets to the value of X-RateLimit-Limit. links: PurgeLemurRequestDataById: $ref: '#/components/links/PurgeLemurRequestDataById' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '404': $ref: '#/components/responses/NotFound' '429': $ref: '#/components/responses/TooManyRequests' '500': $ref: '#/components/responses/InternalServerError' '503': $ref: '#/components/responses/ServiceUnavailable' '504': $ref: '#/components/responses/GatewayTimeout' components: schemas: LemurSummaryParams: x-label: LeMUR summary parameters x-fern-sdk-group-name: lemur type: object allOf: - $ref: '#/components/schemas/LemurBaseParams' - type: object additionalProperties: false properties: answer_format: x-label: Answer format description: > How you want the summary to be returned. This can be any text. Examples: "TLDR", "bullet points" type: string example: transcript_ids: - 47b95ba5-8889-44d8-bc80-5de38306e582 context: This is an interview about wildfires. final_model: anthropic/claude-3-5-sonnet temperature: 0 max_output_size: 3000 LemurSummaryResponse: x-label: LeMUR summary response x-fern-sdk-group-name: lemur type: object allOf: - $ref: '#/components/schemas/LemurStringResponse' example: request_id: 5e1b27c2-691f-4414-8bc5-f14678442f9e response: > - Wildfires in Canada are sending smoke and air pollution across parts of the US, triggering air quality alerts from Maine to Minnesota. Concentrations of particulate matter have exceeded safety levels. - Weather systems are channeling the smoke through Pennsylvania into the Mid-Atlantic and Northeast regions. New York City has canceled outdoor activities to keep children and vulnerable groups indoors. - Very small particulate matter can enter the lungs and impact respiratory, cardiovascular and neurological health. Young children, the elderly and those with preexisting conditions are most at risk. - The conditions causing the poor air quality could get worse or shift to different areas in coming days depending on weather patterns. More wildfires may also contribute to higher concentrations. - Climate change is leading to longer and more severe fire seasons. Events of smoke traveling long distances and affecting air quality over wide areas will likely become more common in the future." usage: input_tokens: 27 output_tokens: 3 LemurBaseParams: x-label: LeMUR base parameters x-fern-sdk-group-name: lemur type: object additionalProperties: false properties: transcript_ids: x-label: Transcript IDs description: > A list of completed transcripts with text. Up to a maximum of 100 files or 100 hours, whichever is lower. Use either transcript_ids or input_text as input into LeMUR. type: array items: x-label: Transcript ID type: string format: uuid input_text: x-label: Input text description: > Custom formatted transcript data. Maximum size is the context limit of the selected model, which defaults to 100000. Use either transcript_ids or input_text as input into LeMUR. type: string context: x-label: Context description: >- Context to provide the model. This can be a string or a free-form JSON value. oneOf: - type: string - type: object additionalProperties: true final_model: x-label: Final model description: > The model that is used for the final prompt after compression is performed. default: default anyOf: - $ref: '#/components/schemas/LemurModel' - type: string x-ts-type: LiteralUnion x-go-type: LeMURModel max_output_size: x-label: Maximum output size description: Max output size in tokens, up to 4000 type: integer default: 2000 temperature: x-label: Temperature description: > The temperature to use for the model. Higher values result in answers that are more creative, lower values are more conservative. Can be any value between 0.0 and 1.0 inclusive. type: number format: float default: 0 minimum: 0 maximum: 1 example: transcript_ids: - 85f9b381-e90c-46ed-beca-7d76245d375e - 7c3acd18-df4d-4432-88f5-1e89f8827eea context: This is an interview about wildfires. final_model: anthropic/claude-3-5-sonnet temperature: 0 max_output_size: 3000 LemurStringResponse: x-label: LeMUR string response x-fern-sdk-group-name: lemur type: object allOf: - type: object additionalProperties: false properties: response: x-label: Response description: The response generated by LeMUR. type: string required: - response - $ref: '#/components/schemas/LemurBaseResponse' example: request_id: 5e1b27c2-691f-4414-8bc5-f14678442f9e response: > Based on the transcript, the following locations were mentioned as being affected by wildfire smoke from Canada: - Maine - Maryland - Minnesota - Mid Atlantic region - Northeast region - New York City - Baltimore usage: input_tokens: 27 output_tokens: 3 Error: x-label: Error type: object additionalProperties: true required: - error properties: error: x-label: Error message description: Error message type: string status: x-label: Status type: string const: error example: error: format_text must be a Boolean LemurModel: x-label: LeMUR model x-fern-sdk-group-name: lemur type: string description: > The model that is used for the final prompt after compression is performed. enum: - anthropic/claude-3-5-sonnet - anthropic/claude-3-opus - anthropic/claude-3-haiku - anthropic/claude-3-sonnet - anthropic/claude-2-1 - anthropic/claude-2 - default - anthropic/claude-instant-1-2 - basic - assemblyai/mistral-7b x-fern-enum: anthropic/claude-3-5-sonnet: description: > Claude 3.5 Sonnet is Anthropic's most intelligent model to date, outperforming Claude 3 Opus on a wide range of evaluations, with the speed and cost of Claude 3 Sonnet. casing: camel: anthropicClaude3_5_Sonnet snake: anthropic_claude3_5_sonnet pascal: AnthropicClaude3_5_Sonnet screamingSnake: ANTHROPIC_CLAUDE3_5_SONNET anthropic/claude-3-opus: description: > Claude 3 Opus is good at handling complex analysis, longer tasks with many steps, and higher-order math and coding tasks. casing: camel: anthropicClaude3_Opus snake: anthropic_claude3_opus pascal: AnthropicClaude3_Opus screamingSnake: ANTHROPIC_CLAUDE3_OPUS anthropic/claude-3-haiku: description: > Claude 3 Haiku is the fastest model that can execute lightweight actions. casing: camel: anthropicClaude3_Haiku snake: anthropic_claude3_haiku pascal: AnthropicClaude3_Haiku screamingSnake: ANTHROPIC_CLAUDE3_HAIKU anthropic/claude-3-sonnet: description: > Claude 3 Sonnet is a legacy model with a balanced combination of performance and speed for efficient, high-throughput tasks. casing: camel: anthropicClaude3_Sonnet snake: anthropic_claude3_sonnet pascal: AnthropicClaude3_Sonnet screamingSnake: ANTHROPIC_CLAUDE3_SONNET anthropic/claude-2-1: description: > Legacy - deprecating on 02/06/25. Claude 2.1 is a legacy model similar to Claude 2.0. The key difference is that it minimizes model hallucination and system prompts, has a larger context window, and performs better in citations. casing: camel: anthropicClaude2_1 snake: anthropic_claude2_1 pascal: AnthropicClaude2_1 screamingSnake: ANTHROPIC_CLAUDE2_1 anthropic/claude-2: description: > Legacy - deprecating on 02/06/25. Claude 2.0 is a legacy model that has good complex reasoning. It offers more nuanced responses and improved contextual comprehension. casing: camel: anthropicClaude2_0 snake: anthropic_claude2_0 pascal: AnthropicClaude2_0 screamingSnake: ANTHROPIC_CLAUDE2_0 default: description: Legacy - deprecating on 02/06/25. The same as Claude 2.0. anthropic/claude-instant-1-2: description: > Legacy - deprecating on 10/28/24. Claude Instant is a legacy model that is optimized for speed and cost. Claude Instant can complete requests up to 20% faster than Claude 2.0. casing: camel: anthropicClaudeInstant1_2 snake: anthropic_claude_instant1_2 pascal: AnthropicClaudeInstant1_2 screamingSnake: ANTHROPIC_CLAUDE_INSTANT1_2 basic: description: Legacy - deprecating on 10/28/24. The same as Claude Instant. assemblyai/mistral-7b: description: > LeMUR Mistral 7B is an LLM self-hosted by AssemblyAI. It's the fastest and cheapest of the LLM options. We recommend it for use cases like basic summaries and factual Q&A. casing: camel: assemblyaiMistral7b snake: assemblyai_mistral7b pascal: AssemblyaiMistral7b screamingSnake: ASSEMBLYAI_MISTRAL7B x-aai-enum: anthropic/claude-3-5-sonnet: label: Claude 3.5 Sonnet (on Anthropic) anthropic/claude-3-opus: label: Claude 3 Opus (on Anthropic) anthropic/claude-3-haiku: label: Claude 3 Haiku (on Anthropic) anthropic/claude-3-sonnet: label: Claude 3 Sonnet (on Anthropic) anthropic/claude-2-1: label: Claude 2.1 (on Anthropic)(Legacy - deprecating on 02/06/25) anthropic/claude-2: label: Claude 2 (on Anthropic)(Legacy - deprecating on 02/06/25) default: label: Default (Legacy - deprecating on 02/06/25) anthropic/claude-instant-1-2: label: Claude Instant 1.2 (on Anthropic)(Legacy - deprecating on 10/28/24) basic: label: Basic (Legacy - deprecating on 10/28/24) assemblyai/mistral-7b: label: Mistral 7B (hosted by AssemblyAI) LemurBaseResponse: x-label: LeMUR base response x-fern-sdk-group-name: lemur type: object additionalProperties: false properties: request_id: x-label: LeMUR request ID description: The ID of the LeMUR request type: string format: uuid usage: $ref: '#/components/schemas/LemurUsage' x-label: Usage description: The usage numbers for the LeMUR request required: - request_id - usage example: request_id: 5e1b27c2-691f-4414-8bc5-f14678442f9e usage: input_tokens: 27 output_tokens: 3 LemurUsage: x-label: Usage description: The usage numbers for the LeMUR request x-fern-sdk-group-name: lemur type: object additionalProperties: false required: - input_tokens - output_tokens properties: input_tokens: x-label: Input tokens description: The number of input tokens used by the model type: integer minimum: 0 output_tokens: x-label: Output tokens description: The number of output tokens generated by the model type: integer minimum: 0 responses: BadRequest: x-label: Bad request description: Bad request content: application/json: schema: $ref: '#/components/schemas/Error' example: error: This is a sample error message Unauthorized: x-label: Unauthorized description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Authentication error, API token missing/invalid NotFound: x-label: Not found description: Not found content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Not found TooManyRequests: x-label: Too many requests description: Too many requests content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Too Many Requests headers: Retry-After: description: The number of seconds to wait before retrying the request schema: type: integer InternalServerError: x-label: Internal server error description: An error occurred while processing the request content: application/json: schema: $ref: '#/components/schemas/Error' example: error: Internal Server Error ServiceUnavailable: x-label: Service unavailable description: Service unavailable GatewayTimeout: x-label: Gateway timeout description: Gateway timeout securitySchemes: ApiKey: type: apiKey in: header name: Authorization ````