Skip to main content
POST
Create a new issue

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, PUT, and DELETE endpoints.

Authorizations

x-api-key
string
header
required

API key for authentication. Must start with dd- prefix.

Headers

x-api-key
string
default:dd-00000000000000000000000065c9cbfe
required

API Key

Body

application/json

Payload for creating a new issue against a TTS generation

generationId
string
required

ID of the generation that has the problem

Example:

"abc123-def456"

generatedText
string
required

Text that was passed to the TTS endpoint

Example:

"Hello world, welcome to Deepdub."

problemWord
string
required

Word (or phrase) that was generated incorrectly

Example:

"Deepdub"

voicePromptId
string
required

ID of the voice prompt used in the generation

Example:

"bd1b00bb-be1c-4679-8eaa-0fcbfd4ff773"

type
enum<string>
default:hallucinations

Category of problem being reported. Omit to default to hallucinations. Any other value returns 400.

Available options:
hallucinations,
glossary
Example:

"hallucinations"

additionalComments
string

Free-form comments describing the problem

Example:

"Mispronunciation of brand name"

problemAudioFile
string

Optional base64-encoded audio clip to attach to the issue

problemSeconds
number

Seconds in the audio where the problem appears

Example:

2.5

phoneticHeard
string

Optional phonetic transcription of how the word actually sounded

Example:

"deep-dubb"

phoneticExpected
string

Optional phonetic transcription of how the word should sound

Example:

"deep-dub"

Response

Issue created

Issue details

id
string
Example:

"iss_12345abcde"

state
enum<string>

Current state of the issue.

Available options:
open,
uploaded_for_correction,
in_progress,
resolved,
rejected
Example:

"open"

rejectionReason
string

Why the issue was rejected. Present only when state is rejected.

Example:

"duplicate report"

createdAt
string<date-time>
updatedAt
string<date-time>
generationId
string
generatedText
string
problemWord
string
voicePromptId
string
type
enum<string>

Category of problem being reported.

Available options:
hallucinations,
glossary
locale
string

Locale of the reported generation, when known.

Example:

"en-US"

additionalComments
string
problemSeconds
number
phoneticHeard
string

Phonetic transcription of how the word actually sounded

phoneticExpected
string

Phonetic transcription of how the word should sound