Speech-to-Text - Unifically

Transcribe audio files to text using ElevenLabs Scribe v2 with word-level timestamps, speaker diarization, and entity detection.

Model

elevenlabs/speech-to-text

Parameters

Parameter	Type	Required	Default	Description
`audio_url`	string	Yes	-	URL of the audio file to transcribe
`language_code`	string	No	auto-detect	ISO 639-1/639-3 language code
`diarize`	boolean	No	`false`	Identify who is speaking (speaker diarization)
`num_speakers`	integer	No	auto	Max number of speakers (up to 32)
`diarization_threshold`	number	No	`0.22`	Higher = fewer speakers, lower = more. Only used when `diarize` is true and `num_speakers` is not set
`timestamps_granularity`	string	No	`word`	`"none"`, `"word"`, or `"character"`
`tag_audio_events`	boolean	No	`true`	Tag events like (laughter), (music), (footsteps)
`entity_detection`	string/array	No	-	Detect entities: `"all"`, or specific types like `"pii"`, `"phi"`, `"pci"`, `"offensive_language"`
`temperature`	number	No	`0`	Randomness (0–2). Higher = more diverse output
`seed`	integer	No	-	Seed for deterministic results (0–2147483647)
`keyterms`	array	No	-	Words/phrases to boost recognition accuracy (max 100, each under 50 chars)
`nsfw_check`	boolean	No	`true`	Check uploaded media inputs for NSFW content

Example - Basic Transcription

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "elevenlabs/speech-to-text",
    "input": {
      "audio_url": "https://example.com/audio.mp3"
    }
  }'

Example - With Diarization

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "elevenlabs/speech-to-text",
    "input": {
      "audio_url": "https://example.com/meeting.mp3",
      "diarize": true,
      "num_speakers": 3,
      "language_code": "en",
      "timestamps_granularity": "word",
      "tag_audio_events": true,
      "entity_detection": "all",
      "keyterms": ["ElevenLabs", "API"]
    }
  }'

Response

{
  "code": 200,
  "success": true,
  "data": {
    "task_id": "abc123def456",
    "status": "processing"
  }
}

Completed Response

{
  "code": 200,
  "success": true,
  "data": {
    "task_id": "abc123def456",
    "status": "completed",
    "output": {
      "language_code": "eng",
      "language_probability": 0.97,
      "text": "Hello world",
      "words": [
        {
          "text": "Hello",
          "start": 0.0,
          "end": 0.5,
          "type": "word",
          "speaker_id": "speaker_0"
        },
        {
          "text": " ",
          "start": 0.5,
          "end": 0.6,
          "type": "spacing"
        },
        {
          "text": "world",
          "start": 0.6,
          "end": 1.0,
          "type": "word",
          "speaker_id": "speaker_0"
        }
      ]
    }
  }
}

Word Object

Each word in the words array contains:

Field	Type	Description
`text`	string	The transcribed text
`start`	number	Start time in seconds
`end`	number	End time in seconds
`type`	string	`"word"`, `"spacing"`, or audio event type
`speaker_id`	string	Speaker identifier (when `diarize` is enabled)

Volume discounts are available for almost all models. Reach out at contact@unifically.com to discuss custom pricing.