GET

/v1/schemas/elevenlabs/audio/v1%2Fspeech-to-text?kind=output

kind outputactivity audiohash 88ce36c5extracted Jul 6, 2026version currentsource upstream spec ↗

Response body

0 properties · 0 required · 0 $defs

This schema isn’t a plain object with properties — showing the raw JSON instead.

application/json
{
  "provider": "elevenlabs",
  "activity": "audio",
  "endpointId": "v1/speech-to-text",
  "kind": "output",
  "contentHash": "88ce36c53c4d504bf431b0f29fc1cd1a2ffcb7a05b25dcfc5bbac7e27eda1f31",
  "specRevision": null,
  "provenance": {
    "sourceUrl": "https://api.elevenlabs.io/openapi.json",
    "sourceHash": "56793d52b38081086c43910ec1916ff4bb286322250511820c239e4f46831396",
    "fetchedAt": 1783328734,
    "extractorVersion": "1"
  },
  "createdAt": 1783328734,
  "supersededAt": null,
  "schema": {
    "anyOf": [
      {
        "$ref": "#/$defs/SpeechToTextChunkResponseModel"
      },
      {
        "$ref": "#/$defs/MultichannelSpeechToTextResponseModel"
      },
      {
        "$ref": "#/$defs/SpeechToTextWebhookResponseModel"
      }
    ],
    "title": "Response Speech To Text V1 Speech To Text Post",
    "oneOf": [
      {
        "$ref": "#/$defs/SpeechToTextChunkResponseModel"
      },
      {
        "$ref": "#/$defs/MultichannelSpeechToTextResponseModel"
      }
    ],
    "$defs": {
      "AdditionalFormatResponseModel": {
        "properties": {
          "requested_format": {
            "type": "string",
            "title": "Requested Format",
            "description": "The requested format."
          },
          "file_extension": {
            "type": "string",
            "title": "File Extension",
            "description": "The file extension of the additional format."
          },
          "content_type": {
            "type": "string",
            "title": "Content Type",
            "description": "The content type of the additional format."
          },
          "is_base64_encoded": {
            "type": "boolean",
            "title": "Is Base64 Encoded",
            "description": "Whether the content is base64 encoded."
          },
          "content": {
            "type": "string",
            "title": "Content",
            "description": "The content of the additional format."
          }
        },
        "type": "object",
        "required": [
          "requested_format",
          "file_extension",
          "content_type",
          "is_base64_encoded",
          "content"
        ],
        "title": "AdditionalFormatResponseModel"
      },
      "DetectedEntity": {
        "properties": {
          "text": {
            "type": "string",
            "title": "Text",
            "description": "The text that was identified as an entity."
          },
          "entity_type": {
            "type": "string",
            "title": "Entity Type",
            "description": "The type of entity detected (e.g., 'credit_card', 'email_address', 'person_name')."
          },
          "start_char": {
            "type": "integer",
            "title": "Start Char",
            "description": "Start character position in the transcript text."
          },
          "end_char": {
            "type": "integer",
            "title": "End Char",
            "description": "End character position in the transcript text."
          }
        },
        "type": "object",
        "required": [
          "text",
          "entity_type",
          "start_char",
          "end_char"
        ],
        "title": "DetectedEntity"
      },
      "MultichannelSpeechToTextResponseModel": {
        "properties": {
          "transcripts": {
            "items": {
              "$ref": "#/$defs/SpeechToTextChunkResponseModel"
            },
            "type": "array",
            "title": "Transcripts",
            "description": "List of transcripts, one for each audio channel. Each transcript contains the text and word-level details for its respective channel."
          },
          "transcription_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Transcription Id",
            "description": "The transcription ID of the response."
          },
          "audio_duration_secs": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Audio Duration Secs",
            "description": "The duration of the audio that was transcribed across all channels in seconds."
          }
        },
        "type": "object",
        "required": [
          "transcripts"
        ],
        "title": "MultichannelSpeechToTextResponseModel",
        "description": "Response model for multichannel speech-to-text transcription.",
        "example": {
          "transcripts": [
            {
              "language_code": "en",
              "language_probability": 0.98,
              "text": "Hello from channel one.",
              "words": [
                {
                  "end": 0.5,
                  "logprob": -0.124,
                  "speaker_id": "speaker_0",
                  "start": 0,
                  "text": "Hello",
                  "type": "word"
                },
                {
                  "end": 0.5,
                  "logprob": 0,
                  "speaker_id": "speaker_0",
                  "start": 0.5,
                  "text": " ",
                  "type": "spacing"
                },
                {
                  "end": 0.8,
                  "logprob": -0.089,
                  "speaker_id": "speaker_0",
                  "start": 0.5,
                  "text": "from",
                  "type": "word"
                }
              ]
            },
            {
              "language_code": "en",
              "language_probability": 0.97,
              "text": "Greetings from channel two.",
              "words": [
                {
                  "end": 0.7,
                  "logprob": -0.156,
                  "speaker_id": "speaker_1",
                  "start": 0.1,
                  "text": "Greetings",
                  "type": "word"
                },
                {
                  "end": 0.7,
                  "logprob": 0,
                  "speaker_id": "speaker_1",
                  "start": 0.7,
                  "text": " ",
                  "type": "spacing"
                },
                {
                  "end": 1,
                  "logprob": -0.078,
                  "speaker_id": "speaker_1",
                  "start": 0.7,
                  "text": "from",
                  "type": "word"
                }
              ]
            }
          ]
        }
      },
      "SpeechToTextCharacterResponseModel": {
        "properties": {
          "text": {
            "type": "string",
            "title": "Text",
            "description": "The character that was transcribed."
          },
          "start": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Start",
            "description": "The start time of the character in seconds."
          },
          "end": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "End",
            "description": "The end time of the character in seconds."
          }
        },
        "type": "object",
        "required": [
          "text"
        ],
        "title": "SpeechToTextCharacterResponseModel",
        "example": {
          "end": 0.1,
          "start": 0,
          "text": "H"
        }
      },
      "SpeechToTextChunkResponseModel": {
        "properties": {
          "language_code": {
            "type": "string",
            "title": "Language Code",
            "description": "The detected language code (e.g. 'eng' for English)."
          },
          "language_probability": {
            "type": "number",
            "title": "Language Probability",
            "description": "The confidence score of the language detection (0 to 1)."
          },
          "text": {
            "type": "string",
            "title": "Text",
            "description": "The raw text of the transcription."
          },
          "words": {
            "items": {
              "$ref": "#/$defs/SpeechToTextWordResponseModel"
            },
            "type": "array",
            "title": "Words",
            "description": "List of words with their timing information."
          },
          "channel_index": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Channel Index",
            "description": "The channel index this transcript belongs to (for multichannel audio)."
          },
          "additional_formats": {
            "anyOf": [
              {
                "items": {
                  "anyOf": [
                    {
                      "$ref": "#/$defs/AdditionalFormatResponseModel"
                    },
                    {
                      "type": "null"
                    }
                  ]
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "title": "Additional Formats",
            "description": "Requested additional formats of the transcript."
          },
          "transcription_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Transcription Id",
            "description": "The transcription ID of the response."
          },
          "entities": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/$defs/DetectedEntity"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "title": "Entities",
            "description": "List of detected entities with their text, type, and character positions in the transcript."
          },
          "audio_duration_secs": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Audio Duration Secs",
            "description": "The duration of the audio that was transcribed in seconds."
          }
        },
        "type": "object",
        "required": [
          "language_code",
          "language_probability",
          "text",
          "words"
        ],
        "title": "SpeechToTextChunkResponseModel",
        "description": "Chunk-level detail of the transcription with timing information.",
        "example": {
          "language_code": "en",
          "language_probability": 0.98,
          "text": "Hello world!",
          "words": [
            {
              "end": 0.5,
              "logprob": -0.124,
              "speaker_id": "speaker_1",
              "start": 0,
              "text": "Hello",
              "type": "word"
            },
            {
              "end": 0.5,
              "logprob": 0,
              "speaker_id": "speaker_1",
              "start": 0.5,
              "text": " ",
              "type": "spacing"
            },
            {
              "end": 1.2,
              "logprob": -0.089,
              "speaker_id": "speaker_1",
              "start": 0.5,
              "text": "world!",
              "type": "word"
            }
          ]
        }
      },
      "SpeechToTextWebhookResponseModel": {
        "properties": {
          "message": {
            "type": "string",
            "title": "Message",
            "description": "The message of the webhook response."
          },
          "request_id": {
            "type": "string",
            "title": "Request Id",
            "description": "The request ID of the webhook response."
          },
          "transcription_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Transcription Id",
            "description": "The transcription ID of the webhook response."
          }
        },
        "type": "object",
        "required": [
          "message",
          "request_id"
        ],
        "title": "SpeechToTextWebhookResponseModel",
        "example": {
          "message": "Request accepted. Transcription result will be sent to the webhook endpoint.",
          "request_id": "1234567890"
        }
      },
      "SpeechToTextWordResponseModel": {
        "properties": {
          "text": {
            "type": "string",
            "title": "Text",
            "description": "The word or sound that was transcribed."
          },
          "start": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "Start",
            "description": "The start time of the word or sound in seconds."
          },
          "end": {
            "anyOf": [
              {
                "type": "number"
              },
              {
                "type": "null"
              }
            ],
            "title": "End",
            "description": "The end time of the word or sound in seconds."
          },
          "type": {
            "type": "string",
            "enum": [
              "word",
              "spacing",
              "audio_event"
            ],
            "title": "Type",
            "description": "The type of the word or sound. 'audio_event' is used for non-word sounds like laughter or footsteps."
          },
          "speaker_id": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "null"
              }
            ],
            "title": "Speaker Id",
            "description": "Unique identifier for the speaker of this word."
          },
          "logprob": {
            "type": "number",
            "title": "Logprob",
            "description": "The log of the probability with which this word was predicted. Logprobs are in range [-infinity, 0], higher logprobs indicate a higher confidence the model has in its predictions."
          },
          "characters": {
            "anyOf": [
              {
                "items": {
                  "$ref": "#/$defs/SpeechToTextCharacterResponseModel"
                },
                "type": "array"
              },
              {
                "type": "null"
              }
            ],
            "title": "Characters",
            "description": "The characters that make up the word and their timing information."
          },
          "channel_index": {
            "anyOf": [
              {
                "type": "integer"
              },
              {
                "type": "null"
              }
            ],
            "title": "Channel Index",
            "description": "The channel this word was spoken on (for multichannel audio). Null for single-channel transcriptions."
          }
        },
        "type": "object",
        "required": [
          "text",
          "type",
          "logprob"
        ],
        "title": "SpeechToTextWordResponseModel",
        "description": "Word-level detail of the transcription with timing information.",
        "example": {
          "characters": [
            {
              "end": 0.1,
              "start": 0,
              "text": "H"
            },
            {
              "end": 0.2,
              "start": 0.1,
              "text": "e"
            },
            {
              "end": 0.3,
              "start": 0.2,
              "text": "l"
            },
            {
              "end": 0.4,
              "start": 0.3,
              "text": "l"
            },
            {
              "end": 0.5,
              "start": 0.4,
              "text": "o"
            }
          ],
          "end": 0.5,
          "logprob": -0.124,
          "speaker_id": "speaker_1",
          "start": 0,
          "text": "Hello",
          "type": "word"
        }
      }
    }
  }
}

Validate a payload

before you spend tokens
shell
$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"elevenlabs","endpointId":"v1/speech-to-text","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}