---
title: "Create transcript evaluation"
method: POST
path: "/v1/transcript-evaluation"
tags: ["Transcript evaluation", "Public-Docs"]
---

# Create transcript evaluation

`POST /v1/transcript-evaluation`

Create a new transcript evaluation definition.

## Request body

- union
  - CreateBooleanTranscriptEvaluation — Create a binary evaluation.
    - `projectID` string, required — ID of the target Voiceflow project.
    - `name` string, required — Name of the evaluation.
    - `description` string, nullable — Description of the evaluation.
    - `enabled` boolean, required — When enabled, evaluations will be run on every new transcript.
    - `prompt` string, required — This prompt describes how the LLM should apply this evaluation.
    - `settings` TranscriptEvaluationSettings
      - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
      - `realtime` object
        - `voice` string
        - `eagerness` string
      - `maxTokens` number
      - `temperature` number
      - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
    - `type` 'boolean', required — The type of binary evaluations.
    - `truePrompt` string, required — This prompt describes which transcripts should evaluate as 'true'.
    - `falsePrompt` string, required — This prompt describes which transcripts should evaluate as 'false'.
  - CreateNumberTranscriptEvaluation — Create a rating evaluation.
    - `projectID` string, required — ID of the target Voiceflow project.
    - `name` string, required — Name of the evaluation.
    - `description` string, nullable — Description of the evaluation.
    - `enabled` boolean, required — When enabled, evaluations will be run on every new transcript.
    - `prompt` string, required — This prompt describes how the LLM should apply this evaluation.
    - `settings` TranscriptEvaluationSettings
      - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
      - `realtime` object
        - `voice` string
        - `eagerness` string
      - `maxTokens` number
      - `temperature` number
      - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
    - `type` 'number', required — The type of rating evaluations.
    - `minimumValue` integer, required — The lowest rating that can be applied.
    - `minimumPrompt` string, required — This prompt describes which transcripts should receive lower ratings.
    - `maximumValue` integer, required — The highest rating that can be applied.
    - `maximumPrompt` string, required — This prompt describes which transcripts should receive higher ratings.
  - CreateStringTranscriptEvaluation — Create a text evaluation.
    - `projectID` string, required — ID of the target Voiceflow project.
    - `name` string, required — Name of the evaluation.
    - `description` string, nullable — Description of the evaluation.
    - `enabled` boolean, required — When enabled, evaluations will be run on every new transcript.
    - `prompt` string, required — This prompt describes how the LLM should apply this evaluation.
    - `settings` TranscriptEvaluationSettings
      - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
      - `realtime` object
        - `voice` string
        - `eagerness` string
      - `maxTokens` number
      - `temperature` number
      - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
    - `type` 'string', required — The type of text evaluations.
  - CreateOptionTranscriptEvaluation — Create a options evaluation.
    - `projectID` string, required — ID of the target Voiceflow project.
    - `name` string, required — Name of the evaluation.
    - `description` string, nullable — Description of the evaluation.
    - `enabled` boolean, required — When enabled, evaluations will be run on every new transcript.
    - `prompt` string, required — This prompt describes how the LLM should apply this evaluation.
    - `settings` TranscriptEvaluationSettings
      - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
      - `realtime` object
        - `voice` string
        - `eagerness` string
      - `maxTokens` number
      - `temperature` number
      - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
    - `type` 'option', required — The type of options evaluations.
    - `options` TranscriptEvaluationOptionSchema[], required — The options that should be evaluated for.
      - `value` string, required
      - `prompt` string, required
      - `included` boolean, required
      - `color` string, required

## Response `201`

- object
  - `evaluation` union, required
    - BooleanTranscriptEvaluation
      - `id` string, required
      - `projectID` string, required
      - `name` string, required
      - `description` string, nullable, required
      - `default` boolean, required
      - `enabled` boolean, required
      - `averageCost` number, nullable, required
      - `prompt` string, required
      - `settings` TranscriptEvaluationSettings, required
        - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
        - `realtime` object
          - `voice` string
          - `eagerness` string
        - `maxTokens` number
        - `temperature` number
        - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
      - `systemTag` string, nullable, required
      - `type` 'boolean', required
      - `truePrompt` string, required
      - `falsePrompt` string, required
    - NumberTranscriptEvaluation
      - `id` string, required
      - `projectID` string, required
      - `name` string, required
      - `description` string, nullable, required
      - `default` boolean, required
      - `enabled` boolean, required
      - `averageCost` number, nullable, required
      - `prompt` string, required
      - `settings` TranscriptEvaluationSettings, required
        - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
        - `realtime` object
          - `voice` string
          - `eagerness` string
        - `maxTokens` number
        - `temperature` number
        - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
      - `systemTag` string, nullable, required
      - `type` 'number', required
      - `minimumValue` number, required
      - `minimumPrompt` string, required
      - `maximumValue` number, required
      - `maximumPrompt` string, required
    - StringTranscriptEvaluation
      - `id` string, required
      - `projectID` string, required
      - `name` string, required
      - `description` string, nullable, required
      - `default` boolean, required
      - `enabled` boolean, required
      - `averageCost` number, nullable, required
      - `prompt` string, required
      - `settings` TranscriptEvaluationSettings, required
        - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
        - `realtime` object
          - `voice` string
          - `eagerness` string
        - `maxTokens` number
        - `temperature` number
        - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
      - `systemTag` string, nullable, required
      - `type` 'string', required
    - OptionTranscriptEvaluation
      - `id` string, required
      - `projectID` string, required
      - `name` string, required
      - `description` string, nullable, required
      - `default` boolean, required
      - `enabled` boolean, required
      - `averageCost` number, nullable, required
      - `prompt` string, required
      - `settings` TranscriptEvaluationSettings, required
        - `model` 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo' | 'gpt-4' | 'gpt-4o' | 'gpt-4o-mini' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano-2025-04-14' | 'gpt-o3-mini' | 'o3-2025-04-16' | 'o4-mini-2025-04-16' | 'gpt-5' | 'gpt-5-mini' | 'gpt-5-nano' | 'gpt-5.2' | 'gpt-5.4' | 'gpt-5.4-mini' | 'gpt-5.5' | 'gpt-realtime' | 'claude-4-opus' | 'claude-4-sonnet' | 'claude-4.5-sonnet' | 'claude-4.6-sonnet' | 'claude-4.5-haiku' | 'claude-4.5-opus' | 'claude-4.7-opus' | 'bedrock-claude-4-sonnet' | 'bedrock-claude-4.5-sonnet' | 'bedrock-claude-4.6-sonnet' | 'bedrock-claude-5-sonnet' | 'bedrock-claude-4.5-haiku' | 'bedrock-claude-4.5-opus' | 'bedrock-claude-4.7-opus' | 'bedrock-claude-4.8-opus' | 'voiceflow-core-4.0' | 'voiceflow-core-4.1' | 'voiceflow-flash-4.1' | 'gemini-2.5-pro' | 'gemini-2.5-flash' | 'gemini-live-2.5-flash' | 'gemini-3-flash' | 'gemini-3.5-flash' | 'gemini-3.1-pro' | 'gpt-oss-20b' | 'gpt-oss-120b' | 'llama-guard-4' | 'llama-3.1-instant' | 'llama-3.3-versatile' | 'qwen3.6-27b' | 'gemini-flash-2' | 'gpt-4-turbo' | 'claude-3.5-haiku' | 'claude-3-opus' | 'claude-3.7-sonnet' | 'claude-v2' | 'llama-3.2-1b-preview' | 'gemini-pro-1.5' | 'claude-3-haiku' | 'claude-3-sonnet' | 'text-davinci-003' | 'claude-v1' | 'claude-instant-v1' | 'deep-seek-r1-distill-llama-70B' | 'claude-3.5-sonnet'
        - `realtime` object
          - `voice` string
          - `eagerness` string
        - `maxTokens` number
        - `temperature` number
        - `reasoningEffort` 'minimal' | 'low' | 'medium' | 'high'
      - `systemTag` string, nullable, required
      - `type` 'option', required
      - `options` TranscriptEvaluationOptionSchema[], required
        - `value` string, required
        - `prompt` string, required
        - `included` boolean, required
        - `color` string, required

---

[API](https://skmtc.net/voiceflow/apis/general-runtime.md) · [All operations](https://skmtc.net/voiceflow/apis/general-runtime/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/voiceflow/general-runtime/versions/6b1c4f778c56/schema)