> ## 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. # Create Voice Clip Set > Create a voice clip set from a call or an uploaded recording. The clips are cut asynchronously: the set is returned in `extracting` status. Poll Get Voice Clip Set until it is `ready`. ## OpenAPI ````yaml https://api.usetuner.ai/public/openapi.json post /api/v1/workspaces/{workspace_id}/agents/{agent_id}/voice-clip-sets 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}/voice-clip-sets: post: tags: - replay-testing summary: Create Voice Clip Set description: >- Create a voice clip set from a call or an uploaded recording. The clips are cut asynchronously: the set is returned in `extracting` status. Poll Get Voice Clip Set until it is `ready`. operationId: >- create_voice_clip_set_api_v1_workspaces__workspace_id__agents__agent_id__voice_clip_sets_post parameters: - 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. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/VoiceClipSetCreateRequest' responses: '202': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/VoiceClipSetResponse' '400': description: >- `source_call_id` or `voice_clip_upload_id` does not exist or belongs to a different agent, or `caller_channel_index` is out of range for the upload. content: application/json: example: detail: Call with ID 123 not found for this agent. schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Missing or invalid API key. content: application/json: example: detail: Not authenticated schema: $ref: '#/components/schemas/ErrorResponse' '402': description: >- Simulation (for a call source) or clip upload analysis (for an upload source) is not included in the workspace's current plan. content: application/json: example: detail: Clip upload analysis not included in your current plan. 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. content: application/json: example: detail: Agent with ID 17 not found schema: $ref: '#/components/schemas/ErrorResponse' '409': description: >- A voice clip set with this name already exists for this agent, or the upload is not awaiting a channel selection or already has a clip set. content: application/json: example: detail: >- A voice clip set named 'Angry customer' already exists for this agent. schema: $ref: '#/components/schemas/ErrorResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - Bearer: [] components: schemas: VoiceClipSetCreateRequest: properties: name: type: string maxLength: 255 minLength: 1 title: Name description: Name of the voice clip set, up to 255 characters. examples: - Angry caller, billing dispute description: anyOf: - type: string maxLength: 10000 - type: 'null' title: Description description: Optional notes about the voice clip set, up to 10,000 characters. examples: - Real call where the caller asks for a refund twice. source_call_id: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Source Call Id description: >- ID of an existing call to take the caller's turns from. Send either this or `voice_clip_upload_id`, not both. examples: - 1234 voice_clip_upload_id: anyOf: - type: integer exclusiveMinimum: 0 - type: 'null' title: Voice Clip Upload Id description: >- ID of an uploaded recording to take the caller's turns from. Send either this or `source_call_id`, not both. examples: - 56 caller_channel_index: anyOf: - type: integer minimum: 0 - type: 'null' title: Caller Channel Index description: >- Index of the channel in the uploaded recording that holds the caller's audio. Required with `voice_clip_upload_id`, and not allowed with `source_call_id`. examples: - 0 extraction_settings: anyOf: - additionalProperties: type: integer type: object - type: 'null' title: Extraction Settings description: >- Optional overrides, in milliseconds, for `merge_gap_ms` (caller segments closer than this are merged into one turn, default 400), `min_turn_ms` (shorter turns are dropped, default 300) and `pad_ms` (padding added around each turn, default 120). Omit to use the defaults. examples: - merge_gap_ms: 400 min_turn_ms: 300 pad_ms: 120 type: object required: - name title: VoiceClipSetCreateRequest description: >- Input schema for creating a voice clip set. The source is exactly one of `source_call_id` or `voice_clip_upload_id`; an upload also needs `caller_channel_index`. VoiceClipSetResponse: properties: id: type: integer title: Id description: Voice clip set ID. name: type: string title: Name description: Name of the voice clip set. description: anyOf: - type: string - type: 'null' title: Description description: Notes about the voice clip set. status: type: string title: Status description: >- `extracting` while the caller's clips are being cut, `ready` once the set can be replayed, or `failed`. clip_count: type: integer title: Clip Count description: Number of clips in the set. total_duration_ms: anyOf: - type: integer - type: 'null' title: Total Duration Ms description: Combined length of all clips in milliseconds. Set once ready. caller_track_duration_ms: anyOf: - type: integer - type: 'null' title: Caller Track Duration Ms description: >- Length of the full caller audio track in milliseconds. Set once ready. source_call_id: anyOf: - type: integer - type: 'null' title: Source Call Id description: ID of the call the set was built from, if it came from a call. source_voice_clip_upload_id: anyOf: - type: integer - type: 'null' title: Source Voice Clip Upload Id description: ID of the upload the set was built from, if it came from an upload. source_channel_mode: anyOf: - type: string - type: 'null' title: Source Channel Mode description: Whether the source recording was `mono` or `multi_channel`. failure_reason: anyOf: - type: string - type: 'null' title: Failure Reason description: Why extraction failed. Set only when `status` is `failed`. transcripts_version: type: integer title: Transcripts Version description: >- Goes up whenever any clip's transcript is edited, verified or unverified. default: 1 verified_count: type: integer title: Verified Count description: Number of clips whose transcript has been verified. default: 0 created_at: type: string format: date-time title: Created At description: When the voice clip set was created. type: object required: - id - name - status - clip_count - created_at title: VoiceClipSetResponse description: A voice clip set, without its clips. 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 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.