no_speech (4105, HTTP 422) · TranscriptFetch API error

No detectable speech (e.g. music/ambient); nothing to transcribe.

Number4105

HTTP status422Unprocessable Entity

Familycontent4xxx · the media has no transcript to give

Example response

JSON

{
  "ok": false,
  "request_id": "req_…",
  "error": {
    "code": "no_speech",
    "number": 4105,
    "message": "No detectable speech (e.g. music/ambient); nothing to transcribe.",
    "docs": "https://transcriptfetch.com/docs/errors/no_speech"
  }
}

Every failure carries error.code, error.number, error.message and error.docs, plus at most one of retry_with (the request change that would succeed), details (structured specifics) or issues (validation problems).

What it means

No speech. No detectable speech (e.g. music/ambient); nothing to transcribe.

Shown to end users as: “This looks like a music or ambient video, there's no speech to transcribe.”

Why it happens

No speech. No detectable speech (e.g. music/ambient); nothing to transcribe.

What to do

Permanent for this input: the same request will fail the same way, so do not retry unchanged. Failed requests are never charged.
AI Fallback Transcription would not help here: there is no accessible speech to transcribe.

Retryable? No, this is permanent for this input. Every error response carries a request_id; include it when contacting support.