Skip to main content
POST
/
api
/
velma-2-stt-batch
Transcribe audio file with automatic language detection
curl --request POST \
  --url https://platform.modulate.ai/api/velma-2-stt-batch \
  --header 'Content-Type: multipart/form-data' \
  --header 'X-API-Key: <api-key>' \
  --form upload_file='@example-file' \
  --form speaker_diarization=true \
  --form emotion_signal=false \
  --form accent_signal=false \
  --form deepfake_signal=false \
  --form pii_phi_tagging=false
{ "text": "Hello, how are you? Bonjour, ça va?", "duration_ms": 5000, "utterances": [ { "utterance_uuid": "e5f6a7b8-c9d0-1234-efab-345678901234", "text": "Hello, how are you?", "start_ms": 0, "duration_ms": 2000, "speaker": 1, "language": "en", "emotion": "Neutral", "accent": "American", "deepfake_score": null }, { "utterance_uuid": "f6a7b8c9-d0e1-2345-fabc-456789012345", "text": "Bonjour, ça va?", "start_ms": 2500, "duration_ms": 2500, "speaker": 2, "language": "fr", "emotion": "Happy", "accent": "British", "deepfake_score": null } ] }

Authorizations

​
X-API-Key
string
header
required

API key used for authentication and usage tracking.

Body

multipart/form-data
​
upload_file
file
required

Audio file to transcribe. Supported formats: AAC, AIFF, FLAC, MP3, MP4, MOV, OGG, Opus, WAV, WebM. Maximum file size: 100MB. Empty files are rejected.

​
speaker_diarization
boolean
default:true

Speaker diarization identifies different speakers in the audio. When enabled, each utterance includes a speaker identifier (e.g., 1, 2).

​
emotion_signal
boolean
default:false

Emotion detection for each utterance. When enabled, each utterance includes an emotion signal detected from the speaker's voice.

​
accent_signal
boolean
default:false

Accent detection for each utterance. When enabled, each utterance includes an accent signal detected from the speaker's voice.

​
deepfake_signal
boolean
default:false

Synthetic voice (deepfake) detection for each utterance. When enabled, each utterance includes a deepfake_score indicating the likelihood that the speech is AI-generated. The score ranges from 0.0 (likely natural) to 1.0 (likely synthetic).

​
pii_phi_tagging
boolean
default:false

PII/PHI tagging in utterance text. When enabled, personally identifiable information and personal health information are wrapped with appropriate tags in the transcription text.

Response

Transcription completed successfully

​
text
string
required

The complete transcribed text from the audio file, containing all utterances concatenated together. This provides a full transcript of the audio content. Always present; may be an empty string when no speech was recognized.

Example:

"Hello everyone. Welcome to the meeting."

​
duration_ms
integer
required

The total duration of the processed audio in milliseconds. This value represents the actual audio duration and is used for usage tracking and billing purposes.

Required range: x >= 0
Example:

45000

​
utterances
object[]
required

Array of individual utterances detected in the audio, ordered by start time. Each utterance represents a continuous segment of speech, potentially from a specific speaker if diarization is enabled. Always present; may be an empty array when no speech was recognized.