Deepfake Detection Streaming

WSS

api

velma-2-synthetic-voice-detection-streaming

Real-time synthetic voice detection over WebSocket. Streams audio to the server and receives per-frame verdicts (synthetic, non-synthetic, or no-content) with confidence scores as analysis windows complete. For a conceptual explanation of how detection works — including windowing, silence trimming, and the no-content verdict — see Deepfake Detection.

Endpoint

wss://platform.modulate.ai/api/velma-2-synthetic-voice-detection-streaming

Authentication

Pass your API key as a query parameter when opening the connection.

wss://platform.modulate.ai/api/velma-2-synthetic-voice-detection-streaming?api_key=YOUR_API_KEY&audio_format=s16le&sample_rate=16000&num_channels=1

Unlike the batch endpoint, the streaming API does not use an X-API-Key header. The key must be in the query string at connection time.

Query parameters

Parameter	Type	Required	Description
`api_key`	string	Yes	Your API key
`audio_format`	string	Yes	Audio encoding format — see Deepfake Detection
`sample_rate`	integer	Conditional	Required for raw (headerless) formats. One of: `8000`, `11025`, `16000`, `22050`, `32000`, `44100`, `48000`, `96000`
`num_channels`	integer	Conditional	Required for raw formats. 1–8

For supported format values and format selection guidance, see Deepfake Detection.

Connection flow

Connect with api_key, audio_format, and (for raw formats) sample_rate and num_channels.
Stream audio as binary WebSocket frames. Frames can be any size.
Receive frame JSON messages as analysis windows complete.
Send an empty text frame ("") to signal end of audio.
Receive a done message with total duration and frame count.
The connection closes automatically.

Server messages

Frame result

Sent each time an analysis window is complete.

{
  "type": "frame",
  "frame": {
    "start_time_ms": 0,
    "end_time_ms": 4000,
    "verdict": "synthetic",
    "confidence": 0.9732
  }
}

Field	Type	Description
`start_time_ms`	integer	Frame start time in the audio stream (ms)
`end_time_ms`	integer	Frame end time in the audio stream (ms)
`verdict`	string	`"synthetic"`, `"non-synthetic"`, or `"no-content"`
`confidence`	float	Confidence in the verdict, 0.0–1.0

Done

{
  "type": "done",
  "duration_ms": 12500,
  "frame_count": 10
}

Field	Type	Description
`duration_ms`	integer	Total duration of the streamed audio in milliseconds
`frame_count`	integer	Total number of frames analyzed

Error

{
  "type": "error",
  "error": "Invalid audio_format='mid'. Valid values: ['3g2', '3ga', ...]"
}

WebSocket close codes

Code	Meaning
`1000`	Normal closure after a successful `done` message
`1003`	Invalid query parameters (bad format, sample rate, or channels)
`1011`	Internal server error
`4001`	The `api_key` query parameter is missing or invalid
`4002`	Audio could not be decoded or does not match the declared format
`4003`	The request is not permitted
`4004`	The API key does not have access to this model
`4029`	Insufficient credits
`4030`	Concurrent request limit reached
`4031`	Monthly usage limit reached

An error JSON message is sent before the connection closes (except on 1000).

Rate limits

Concurrent connection limits apply per model.
A connection that exceeds a limit closes with 4029 (insufficient credits), 4030 (concurrent request limit), or 4031 (monthly usage limit).

Deepfake Detection — windowing, silence trimming, and scoring explained
Deepfake Detection — format options for the streaming endpoint
Which API should I use? — batch vs streaming tradeoffs
Authentication and rate limits

Messages

query

type:object

Frame Result

type:object

A single frame detection result.

Done

type:object

Analysis complete - all frames have been delivered.

Error

type:object

An error occurred during connection or analysis.

Audio Data

type:string

A binary frame containing audio samples.

End of Stream

type:string

An empty text frame signalling that the client has finished sending audio.

Messages

Velma

Speech-to-text Transcription