> ## Documentation Index > Fetch the complete documentation index at: https://docs.deepdub.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create a new issue > Report a problem with a TTS generation by creating a new issue. Issues are tracked internally by the Deepdub team and used to improve voice quality. The `problemAudioFile` field can optionally include base64-encoded audio attached to the issue, and `problemSeconds` indicates the timestamp in the audio where the problem appears. ## Reporting generation problems Use this endpoint to flag a TTS generation that didn't sound right — a mispronunciation, an unwanted artifact, or any other quality issue. Reports are reviewed by the Deepdub team and feed into model improvements. To make a report actionable, include: * `generationId` — the ID of the affected generation * `generatedText` — the exact text passed to TTS * `problemWord` — the specific word or phrase that was generated incorrectly * `voicePromptId` — the voice prompt that was used * `problemSeconds` — timestamp (in seconds) where the problem occurs * `type` *(optional)* — `hallucinations` (the default) or `glossary` * `phoneticHeard` *(optional)* — how the word actually sounded, written phonetically * `phoneticExpected` *(optional)* — how the word should have sounded, written phonetically * `problemAudioFile` *(optional)* — base64-encoded clip of the problem audio * `additionalComments` *(optional)* — anything else that helps reproduce or explain the issue Use `type` to say what kind of problem you're reporting: `hallucinations` for words the model got wrong or invented, `glossary` for terms that need a permanent pronunciation entry. Omitting it defaults to `hallucinations`; any other value returns `400`. The `phoneticHeard` and `phoneticExpected` pair is the fastest way to make a mispronunciation actionable — it tells the team exactly what the model produced and what it should have produced, without anyone having to listen to the audio. The response includes an `id` you can use with the [GET](/api-reference/issues/get-issue), [PUT](/api-reference/issues/update-issue), and [DELETE](/api-reference/issues/delete-issue) endpoints. ## OpenAPI ````yaml post /issues openapi: 3.0.0 info: title: Deepdub API description: >- Deepdub's Text-to-Speech API enables high-quality, expressive speech generation with voice cloning, accent control, and real-time streaming capabilities. contact: email: support@deepdub.ai version: '1.0' servers: - url: https://restapi.deepdub.ai/api/v1 description: US (default) - url: https://restapi.eu.deepdub.ai/api/v1 description: EU security: - ApiKeyAuth: [] externalDocs: description: OpenAPI url: https://restapi.deepdub.ai/api/v1/swagger/index.html paths: /issues: post: tags: - Issues summary: Create a new issue description: >- Report a problem with a TTS generation by creating a new issue. Issues are tracked internally by the Deepdub team and used to improve voice quality. The `problemAudioFile` field can optionally include base64-encoded audio attached to the issue, and `problemSeconds` indicates the timestamp in the audio where the problem appears. operationId: createIssue parameters: - description: API Key name: x-api-key in: header required: true schema: type: string default: dd-00000000000000000000000065c9cbfe example: dd-00000000000000000000000065c9cbfe requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/model.CreateIssueRequest' example: generationId: abc123-def456 generatedText: Hello world, welcome to Deepdub. problemWord: Deepdub voicePromptId: bd1b00bb-be1c-4679-8eaa-0fcbfd4ff773 additionalComments: Mispronunciation of brand name problemSeconds: 2.5 responses: '201': description: Issue created content: application/json: schema: $ref: '#/components/schemas/model.IssueResponse' '400': description: Bad request — missing required fields content: application/json: schema: $ref: '#/components/schemas/model.IssueErrorResponse' example: message: generationId is required '401': description: Unauthorized — invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/model.IssueErrorResponse' example: message: Unauthorized '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/model.IssueErrorResponse' example: message: Failed to create issue components: schemas: model.CreateIssueRequest: description: Payload for creating a new issue against a TTS generation type: object required: - generationId - generatedText - problemWord - voicePromptId properties: generationId: description: ID of the generation that has the problem type: string example: abc123-def456 generatedText: description: Text that was passed to the TTS endpoint type: string example: Hello world, welcome to Deepdub. problemWord: description: Word (or phrase) that was generated incorrectly type: string example: Deepdub voicePromptId: description: ID of the voice prompt used in the generation type: string example: bd1b00bb-be1c-4679-8eaa-0fcbfd4ff773 type: description: >- Category of problem being reported. Omit to default to `hallucinations`. Any other value returns 400. type: string enum: - hallucinations - glossary default: hallucinations example: hallucinations additionalComments: description: Free-form comments describing the problem type: string example: Mispronunciation of brand name problemAudioFile: description: Optional base64-encoded audio clip to attach to the issue type: string problemSeconds: description: Seconds in the audio where the problem appears type: number example: 2.5 phoneticHeard: description: Optional phonetic transcription of how the word actually sounded type: string example: deep-dubb phoneticExpected: description: Optional phonetic transcription of how the word should sound type: string example: deep-dub model.IssueResponse: description: Issue details type: object properties: id: type: string example: iss_12345abcde state: description: Current state of the issue. type: string enum: - open - uploaded_for_correction - in_progress - resolved - rejected example: open rejectionReason: description: Why the issue was rejected. Present only when `state` is `rejected`. type: string example: duplicate report createdAt: type: string format: date-time updatedAt: type: string format: date-time generationId: type: string generatedText: type: string problemWord: type: string voicePromptId: type: string type: description: Category of problem being reported. type: string enum: - hallucinations - glossary locale: description: Locale of the reported generation, when known. type: string example: en-US additionalComments: type: string problemSeconds: type: number phoneticHeard: description: Phonetic transcription of how the word actually sounded type: string phoneticExpected: description: Phonetic transcription of how the word should sound type: string model.IssueErrorResponse: description: Error response from the issues endpoints type: object properties: message: type: string example: Issue not found securitySchemes: ApiKeyAuth: type: apiKey in: header name: x-api-key description: API key for authentication. Must start with `dd-` prefix. ````