Saltar al cuntegna

Cohere Transcribe

Integrar

ID dal model cohere-transcribe
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/cohere-transcribe?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Datotecas sco l'exempel: $0,001 1 credit API · ≈ ₽0,11 tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
Cohere Discurrer a text #speech#transcribe#stt

Model speech-to-text cun 14 linguas tscherniblas ed in switch opziunal per la punctuaziun

Cohere · Text

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e ​​il pretsch s'actualiseschan durant che ti als midas.

•obligatori audio_url
Trametta in datoteca u

URL da la datoteca audio per la transcripziun. Formats acceptads includan flac, ogg, webm, wav, m4a, mpga, mpeg, mp4 e mp3.

Avanzà language · max_new_tokens · punctuation
standard en

Identifitgescha la lingua da l'audio cun in da quests codes ISO 639-1: en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar.

standard 256

Limit da tokens generads per mintga part audio.

POST /run/cohere-transcribe?wait=20 calculaziun → $0,001
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/cohere-transcribe?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Executar questa dumonda

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Obtegnair ina clav API

Davart Cohere Transcribe

Transcriva ina datoteca audio da `audio_url` (mp3, mp4, mpeg, mpga, m4a, wav, webm, ogg u flac) en text. `language` accepta en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi u ar, cun en sco standard. `punctuation` po vegnir deactivà, e `max_new_tokens` (1 fin 1014) limita l'output per mintga segment audio.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun
audio_urlobligatori audio
Tipurl · audio
URL da la datoteca audio per la transcripziun. Formats acceptads includan flac, ogg, webm, wav, m4a, mpga, mpeg, mp4 e mp3.
languageopziunal
Tipenum
Standarden
enfrdeitesptelnlplzhjakoviar
Identifitgescha la lingua da l'audio cun in da quests codes ISO 639-1: en, fr, de, it, es, pt, el, nl, pl, zh, ja, ko, vi, ar.
punctuationopziunal
Tipboolean
Standardtrue
Controlla sche il text d'output cuntegna maiusclas e interpuncziun.
max_new_tokensopziunal
Tipinteger
Standard256
1 – 1 014
Limit da tokens generads per mintga part audio.
obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "cohere-transcribe",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1,
    "usd": "0.001",
    "charged": 1,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "text": "string",
    "timings": {}
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.
La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.
Champs da l'output
text
stringText obtegnì tras la transcripziun da la datoteca audio.
timings
objectDetagls dals temps da prestaziun, mesirads en secundas.

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/cohere-transcribe.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt