Saltar al cuntegna

Elevenlabs - Forced Alignment

Integrar

ID dal model elevenlabs/forced-alignment
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/elevenlabs/forced-alignment?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",
    "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

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

Datotecas sco l'exempel: $0,22 220 credits API tias datotecas vegnan mesiradas avant l'execuziun Lantschar sin questa pagina

Obtegna ina clav API
ElevenLabs Discurrer a text #forced-alignment#speech-to-text

Allignescha ina transcripziun enconuschenta cun ina registraziun audio e returna il timing da pleds e caracters

ElevenLabs · Datas (JSON)

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 88 / 675000

Transcripziun il text da la quala sto vegnir allineà cun l'audio.

•obligatori audio_url
Trametta in datoteca u

Furnescha l'audio d'allineament tras ina URL da datoteca, cun ils limits da 10 uras durada e 3 GB grondezza.

POST /run/elevenlabs/forced-alignment?wait=20 calculaziun → $0,22
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/elevenlabs/forced-alignment?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",
    "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/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 Elevenlabs - Forced Alignment

Confrunta ina transcripziun existenta cun sia registraziun. Furnescha `audio_url` e `text`; il text po avair fin a 675,000 caracters. La datoteca audio po avair fin a 3 GB e durar 10 uras. L'output enumerescha l'allineament a nivel da caracter e pled, sco era la perdita d'allineament media.

Parameters

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

NumTip StandardPermess Descripziun
audio_urlobligatori audio
Tipurl · audio
Furnescha l'audio d'allineament tras ina URL da datoteca, cun ils limits da 10 uras durada e 3 GB grondezza.
textobligatori
Tipstring
≤ 675 000 caracters
Transcripziun il text da la quala sto vegnir allineà cun l'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": "elevenlabs/forced-alignment",
  "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": 220,
    "usd": "0.22",
    "charged": 220,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "text": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "characters": [
      {
        "text": "string",
        "start": 1.0,
        "end": 1.0
      }
    ],
    "words": [
      {
        "text": "string",
        "start": 1.0,
        "end": 1.0,
        "loss": 1.0
      }
    ],
    "loss": 1.0
  },
  "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.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/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
characters
array of object {text, start, end}Infurmaziuns d'allineament per singuls caracters.
words
array of object {text, start, end, loss}Infurmaziuns d'allineament per singuls pleds.
loss
numberPerdita media d'allineament en l'entira transcripziun.

Dapli models: Discurrer a text

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