> ## Documentation Index > Fetch the complete documentation index at: https://docs.usetuner.ai/llms.txt > Use this file to discover all available pages before exploring further. # Re-score Transcription Accuracy > Re-score one clip-replay call against the clips' current transcripts. Runs synchronously (a text comparison only) and returns the refreshed accuracy block. Clip edits never re-score on their own; this is how an outdated score is brought up to date. On an unexpected error the old score is left untouched. ## OpenAPI ````yaml https://api.usetuner.ai/public/openapi.json post /api/v1/workspaces/{workspace_id}/agents/{agent_id}/calls/{call_id}/transcription-accuracy/rescore openapi: 3.1.0 info: title: Tuner API description: >- Send calls to Tuner and manage agents, evaluation settings, simulations and workspace settings. version: 1.0.0 servers: - url: https://api.usetuner.ai security: [] tags: - name: calls description: Send call recordings and transcripts to Tuner and retrieve call details. x-group: Calls - name: workspaces description: >- Manage your workspaces, the API keys used to access them, and their PII redaction and data retention settings. x-group: Workspaces - name: simulation description: >- Run simulated calls against your agents, manage simulation profiles, and look up the caller personas and background-noise environments they can use. x-group: Simulation - name: scenarios description: Manage the test scenarios that simulated calls follow. x-group: Scenarios - name: replay-testing description: >- Replay recorded caller audio against a new version of your agent: upload or extract voice clips from real calls, then run them as replay runs. x-group: Replay Testing - name: agents description: Create, update and list the voice agents connected to your workspace. x-group: Agents - name: agent-settings description: >- Configure how Tuner evaluates an agent's calls, including evaluations, call outcomes, intents, data extraction, rules and alerts, plus the agent's SIP and outbound call configuration. x-group: Agent Settings - name: traces description: Send OpenTelemetry traces from your agent to Tuner. x-group: Traces - name: providers description: List the voice providers Tuner can connect to. x-group: Providers paths: /api/v1/workspaces/{workspace_id}/agents/{agent_id}/calls/{call_id}/transcription-accuracy/rescore: post: tags: - calls - calls summary: Re-score Transcription Accuracy description: >- Re-score one clip-replay call against the clips' current transcripts. Runs synchronously (a text comparison only) and returns the refreshed accuracy block. Clip edits never re-score on their own; this is how an outdated score is brought up to date. On an unexpected error the old score is left untouched. operationId: >- rescore_call_transcription_accuracy_api_v1_workspaces__workspace_id__agents__agent_id__calls__call_id__transcription_accuracy_rescore_post parameters: - name: call_id in: path required: true schema: type: integer description: Tuner's internal numeric ID for the call. title: Call Id description: Tuner's internal numeric ID for the call. - name: agent_id in: path required: true schema: type: integer description: Tuner's internal numeric ID for the agent. title: Agent Id description: Tuner's internal numeric ID for the agent. - name: workspace_id in: path required: true schema: type: integer description: Workspace ID. Find this in Workspace > General Settings. title: Workspace Id description: Workspace ID. Find this in Workspace > General Settings. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/TranscriptionAccuracy' '401': description: Missing or invalid API key. content: application/json: example: detail: Not authenticated schema: $ref: '#/components/schemas/ErrorResponse' '403': description: You do not have access to this workspace. content: application/json: example: detail: User does not have access to workspace 42 schema: $ref: '#/components/schemas/ErrorResponse' '404': description: Agent not found, or the call is not a replay of this agent. content: application/json: example: detail: Call with ID 88 not found schema: $ref: '#/components/schemas/ErrorResponse' '409': description: >- The call can't be scored (the reason is in the message); its old score was removed. Also returned, with nothing removed, while the replay is still running. content: application/json: example: detail: >- This call can't be scored: the clips it played have fewer than 10 words to compare. schema: $ref: '#/components/schemas/ErrorResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Bearer: [] components: schemas: TranscriptionAccuracy: properties: score: type: number title: Score description: Accuracy from 0 to 1 (1 minus the error rate, floored at 0) error_rate: type: number title: Error Rate description: Raw word error rate. Can exceed 1 when much noise was transcribed band: type: string enum: - good - fair - poor title: Band description: Quality band for the score reference_word_count: type: integer title: Reference Word Count description: Words the caller said (after cleaning) hypothesis_word_count: type: integer title: Hypothesis Word Count description: Words the agent heard (after cleaning) wrong_count: type: integer title: Wrong Count description: Caller words that were misheard missed_count: type: integer title: Missed Count description: Caller words that were not transcribed extra_count: type: integer title: Extra Count description: Transcribed words the caller did not say errors: items: $ref: '#/components/schemas/TranscriptionErrorEntry' type: array title: Errors description: >- Up to 50 mismatches in reading order. See `error_entry_count` for the total error_entry_count: type: integer title: Error Entry Count description: >- Total number of mismatch entries, including those beyond the 50 stored language: type: string title: Language description: Language code the comparison used stt_provider: anyOf: - type: string - type: 'null' title: Stt Provider description: Raw speech-to-text provider name. Null when not reported stt_model: anyOf: - type: string - type: 'null' title: Stt Model description: Raw speech-to-text model name. Null when not reported partial_playback: type: boolean title: Partial Playback description: True when the call ended before every clip was played clips_total: type: integer title: Clips Total description: Clips in the set when the call was scored clips_scored: type: integer title: Clips Scored description: Clips that were played and compared clips_verified: type: integer title: Clips Verified description: How many of the scored clips are human-verified right now last_verified_at: anyOf: - type: string format: date-time - type: 'null' title: Last Verified At description: Latest verification time among the verified scored clips clips: items: $ref: '#/components/schemas/TranscriptionClipReference' type: array title: Clips description: The scored clips in playback order, with their current text is_outdated: type: boolean title: Is Outdated description: >- True when clip transcripts were edited or verified after this call was scored, or the scoring rules changed. Re-score the call to use the current transcripts. False when the clip set no longer exists calculated_at: type: string format: date-time title: Calculated At description: When the score was calculated type: object required: - score - error_rate - band - reference_word_count - hypothesis_word_count - wrong_count - missed_count - extra_count - error_entry_count - language - partial_playback - clips_total - clips_scored - clips_verified - is_outdated - calculated_at title: TranscriptionAccuracy description: >- How accurately the agent's speech-to-text heard the replayed caller clips. The score fields are stored when the call was scored. The verification fields, ``clips`` and ``is_outdated`` are read live from the clip set. Absent (null) on the parent when the call has no score. ErrorResponse: properties: detail: type: string title: Detail description: Human-readable description of what went wrong. type: object required: - detail title: ErrorResponse description: Error body returned when a request fails. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError TranscriptionErrorEntry: properties: kind: type: string enum: - wrong - missed - extra title: Kind description: >- 'wrong' = misheard (a different word was transcribed), 'missed' = said but not transcribed, 'extra' = transcribed but not said said: anyOf: - type: string - type: 'null' title: Said description: What the caller said (original clip text). Null for 'extra' heard: anyOf: - type: string - type: 'null' title: Heard description: What the agent heard (transcribed text). Null for 'missed' clip_index: anyOf: - type: integer - type: 'null' title: Clip Index description: turn_index of the clip that owns the said words. Null for 'extra' from_verified_clip: type: boolean title: From Verified Clip description: True when the owning clip's reference text was human-verified type: object required: - kind - from_verified_clip title: TranscriptionErrorEntry description: >- One mismatch between what the caller said and what the agent's speech-to-text heard. TranscriptionClipReference: properties: turn_index: type: integer title: Turn Index description: Zero-based position of the clip within the set reference_transcript: anyOf: - type: string - type: 'null' title: Reference Transcript description: Current reference text of the clip. Null when it has no text verified: type: boolean title: Verified description: True when the clip's text was human-verified type: object required: - turn_index - verified title: TranscriptionClipReference description: >- Current reference text of one scored clip (live data, not frozen at scoring time). ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError securitySchemes: Bearer: type: http description: >- Use Tuner API key (tr_api_...) or user session token. Find your API key in Workspace Settings > API Keys. scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.