Home / Tools / helve.audio_transcribe

Durable Batch Audio/Video Transcription

Metered

Tool ID: helve.audio_transcribe

Submit an audio or video URL for durable batch transcription via AssemblyAI, Deepgram, or ElevenLabs Scribe. Returns a job ID to poll at GET /v1/jobs/{id}.

Provider
helve
Category
Audio Transcription
Pricing
$0.15–$0.26/hr audio (+15% Helve fee), billed only on completion
Replaces Signup
Replaces AssemblyAI, Deepgram, and ElevenLabs accounts
Get API Key ($0.50 Free Credit) Browse All 223 Tools

Input Parameters

ParameterTypeRequiredDescription
audio_urlstringRequiredHTTPS URL of the recording, fetched by the provider. Signed URLs are fine; it must stay reachable until the provider has read it. No embedded credentials or fragments.
providerstring (assemblyai | deepgram | elevenlabs | auto)OptionalWhich speech-to-text provider runs the job. `auto` (default) picks the first configured provider. The choice is persisted on the job before execution.
languagestringOptionalBCP-47-style language tag such as `en` or `en-US`. Omit to let the provider detect the language.
diarizebooleanOptionalLabel speakers in `words` as `speaker_0`, `speaker_1`, … in order of first appearance. Default false.
keytermsarrayOptionalRecognition hints: names, jargon, product terms. Supported on AssemblyAI, Deepgram Nova-3, and ElevenLabs Scribe v2; other models ignore them with a warning.
timestampsstring (word | none)Optional`word` (default) returns per-word timings in `result.words`; `none` omits them.
strictbooleanOptionalWhen true, any option the selected provider or model cannot honour rejects the request instead of producing a warning. Default false.
provider_optionsobjectOptionalProvider-native options, validated by the adapter. Model selection lives here. Transport settings such as URLs, callbacks, and authentication cannot be overridden.

Call via REST API

curl -X POST https://helve.dev/v1/tools/call \
  -H "Authorization: Bearer sk_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "tool_id": "helve.audio_transcribe",
  "arguments": {
    "audio_url": "https://example.com/meeting.mp3",
    "diarize": true
  }
}'

Call via MCP (call_tool)

{
  "name": "call_tool",
  "arguments": {
    "tool_id": "helve.audio_transcribe",
    "arguments": {
      "audio_url": "https://example.com/meeting.mp3",
      "diarize": true
    }
  }
}