Media and Speech Processing
stt short
Speech to text for short clips: transcribe an audio or video recording of up to 60 seconds, sent as base64 file upload or public URL (mp3, wav, m4a, aac, ogg, opus, flac, mp4, webm), at a fixed 0.01 USDC per call. Returns the transcript with punctuation, detected or requested language, utterances, word timestamps and confidence values. The length is measured first; a longer file is refused and not charged. Longer files: /v1/stt. Many files: /v1/stt-batch.
POST https://medien.halowerk.com/v1/stt-shortInputs
| Field | Type | Required | Description |
|---|---|---|---|
| source | object, string | No | The recording, at most 60 seconds: an object with url or content_base64, or a URL string. |
| audio_url | string | No | Shorthand for source.url. |
| url | string | No | Shorthand for source.url. |
| content_base64 | string | No | Shorthand for source.content_base64. |
| audio_base64 | string | No | Shorthand for source.content_base64. |
| filename | string | No | File name for a shorthand base64 upload. |
| language | string | No | BCP-47 code such as en, de, es, fr. Omit to detect the language automatically. Multilingual mode is not offered on this fixed-price path; use /v1/stt with language "multi". |
| include_words | boolean | No | Return every word with start, end and confidence. Off returns text, utterances and paragraphs only. |
| duration_minutes | number | No | Accepted for compatibility with /v1/stt request bodies and ignored: the price is fixed and the length is measured. |
| duration_seconds | number | No | Accepted and ignored; the length is measured. |
Show full input schema
{
"type": "object",
"additionalProperties": false,
"properties": {
"source": {
"type": [
"object",
"string"
],
"additionalProperties": false,
"description": "The recording, at most 60 seconds: an object with url or content_base64, or a URL string.",
"properties": {
"url": {
"type": "string",
"maxLength": 2048,
"description": "Public http(s) URL of the audio or video file."
},
"content_base64": {
"type": "string",
"maxLength": 11500000,
"description": "The file as base64 upload (a data: URI prefix is accepted), at most 8 MB decoded."
},
"filename": {
"type": "string",
"maxLength": 260,
"description": "Optional file name; helps format detection."
}
}
},
"audio_url": {
"type": "string",
"maxLength": 2048,
"description": "Shorthand for source.url."
},
"url": {
"type": "string",
"maxLength": 2048,
"description": "Shorthand for source.url."
},
"content_base64": {
"type": "string",
"maxLength": 11500000,
"description": "Shorthand for source.content_base64."
},
"audio_base64": {
"type": "string",
"maxLength": 11500000,
"description": "Shorthand for source.content_base64."
},
"filename": {
"type": "string",
"maxLength": 260,
"description": "File name for a shorthand base64 upload."
},
"language": {
"type": "string",
"maxLength": 12,
"description": "BCP-47 code such as en, de, es, fr. Omit to detect the language automatically. Multilingual mode is not offered on this fixed-price path; use /v1/stt with language \"multi\"."
},
"include_words": {
"type": "boolean",
"default": true,
"description": "Return every word with start, end and confidence. Off returns text, utterances and paragraphs only."
},
"duration_minutes": {
"type": "number",
"description": "Accepted for compatibility with /v1/stt request bodies and ignored: the price is fixed and the length is measured."
},
"duration_seconds": {
"type": "number",
"description": "Accepted and ignored; the length is measured."
}
}
}Published input example
{
"source": {
"url": "https://medien.halowerk.com/beispiel/interview.mp3"
},
"language": "en"
}Result & documentation
Show published result schema
{
"$ref": "https://medien.halowerk.com/v1/stt-short/schema#/outputSchema"
}Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-19 UTC.
More endpoints in this hub
- Media and Speech Processing0.03 USDC · variable
ad detect
POSThttps://medien.halowerk.com/v1/ad-detectTakes a podcast episode of up to 120 minutes and returns its advertising segments: paid sponsor reads, self-promotion (newsletter, Patreon, merchandise) and cross-promotion of other shows, each with start and end on sentence boundaries, the
- Media and Speech Processing0.004 USDC · variable
audio concat
POSThttps://medien.halowerk.com/v1/audio-concatTakes 2 to 10 audio or video files (each up to 24 MB, together up to 60 minutes) and joins their audio in the given order. Between parts either a pause of chosen length or a crossfade is placed; optionally every part is brought to a common
- Media and Speech Processing0.01 USDC
audio confidence review
POSThttps://medien.halowerk.com/v1/audio-confidence-reviewReturn the least confident recognized passages with exact listening timestamps. Only audio_url is required. Duration is measured locally and capped at20seconds before Deepgram EU processing; training opt-out sent on every request. Failed wo