Njuolgga sisdollui

Zonos2 Text to Speech

Integrere

Modealla-id zonos2
# 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/zonos2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "reference_audio_url": "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Gitta 0,02 $ juohke ráŋggas mákso duohta geavaheami mielde, loahppa máhcaheami Vuodje dán siiddu alde

Oza API-čoavdaga
Zyphra Teavsttas hállan Referánsa-inputtat #text-to-speech#tts#voice-cloning

Máŋggagielat jietaklonen-TTS sampling-heivehemiiguin ja molssaeavttuin lagas ovttastahttimii dahje ilbmaveahkkái

Zyphra · Jietna

Dát lea du vuosttaš bohtos

Daga jearaldaga vuolábealde ja vuodje dan iežat API-čoavddain. Boađusat kopierejuvvojit min vurkemii, bisuhuvvojit álo dahje 7 beaivvi nuvttá.

Ráhkat jearaldaga

Kontrollat ráhkaduvvojit modealla skeama vuođul. Koda ja haddi ođasmahttojuvvojit go rievddadat daid.

•gáibiduvvo
Luoitte fiilla, dahje

Jietna mii addá jiena gáldu klonemii.

Viiddiduvvon language · temperature · top_p · min_p · top_k · max_tokens · seed · accurate_mode · clean_speaker_background · enable_safety_checker
standárda en_us

Giela válljen teavstta normaliseremii, mii guođđojuvvo jus koda ii leat okta dáin: en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn, ko.

standárda 1.15

Temperatuvra samplinga várás.

standárda 0

Nucleus-samplinga probábilitehta; bidde 0:s heaitti dihte dan.

standárda 0.18

Minimum-probábilitehta samplinga probábilitehta-rádja.

standárda 106

Top-k-samplinga ráddjehus; bidde 0:s heaitti dihte dan.

Jiena-rámma ráhkadeami rájá, mas geavahuvvo modealla konteakstaráddjehus, jus eará maksima ii leat addojuvvon.

Seed, mii dahká boađosiid geardduhahttin; válljejuvvo ozanlaččat, jos ii leat addon.

POST /run/zonos2?wait=20 haddemearrádus → 0,02 $
# 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/zonos2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "reference_audio_url": "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Geavat dán ohcamuša

Du key báhcá dán fierpmádatlogan: dat sáddejuvvo dušše Doitong API:ii ja vurkejuvvo (localStorage) dušše jos válljet Remember. Viečča API-keya

Dát lea Zonos2 Text to Speech birra

Klonet jiena `reference_audio_url`-s ja lohká teavstta, máhcaha WAV-jiena 44.1kHz mono-hámis ovttas geavahuvvon seed:in. `language` mearrida teavstta normaliserema en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn ja ko várás. `accurate_mode` lonuha jienalagasvuođa ilbmaveahkiin, ja sampling sáhttá heivehuvvot `temperature`, `top_p`, `min_p`, `top_k` ja `max_tokens` (gitta 6144 rádjái) bokte.

Parametterat

NammaŠládja StandárdaDohkkehuvvon Govvádus
reference_audio_urlgáibiduvvo
Šládjaurl · audio
Jietna mii addá jiena gáldu klonemii.
languageeaktodáhtolaš
Šládjastring
Standárdaen_us
Giela válljen teavstta normaliseremii, mii guođđojuvvo jus koda ii leat okta dáin: en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn, ko.
seedeaktodáhtolaš
Šládjainteger | null
0 – 2 147 483 647
Seed, mii dahká boađosiid geardduhahttin; válljejuvvo ozanlaččat, jos ii leat addon.
accurate_modeeaktodáhtolaš
Šládjaboolean
Standárdatrue
Jiena ovttastahttin ja izraivealašvuohta: True eaktuda lagabut ovttastahttima, muhto False eaktuda izraivealaseappot jiena.
clean_speaker_backgroundeaktodáhtolaš
Šládjaboolean
Standárdafalse
Čájeha ahte referánsa-jienas lea čáhppes duogáš.
temperatureeaktodáhtolaš
Šládjanumber
Standárda1.15
0 – 2
Temperatuvra samplinga várás.
top_peaktodáhtolaš
Šládjanumber
Standárda0
0 – 1
Nucleus-samplinga probábilitehta; bidde 0:s heaitti dihte dan.
min_peaktodáhtolaš
Šládjanumber
Standárda0.18
0 – 1
Minimum-probábilitehta samplinga probábilitehta-rádja.
top_keaktodáhtolaš
Šládjainteger
Standárda106
0 – 2 048
Top-k-samplinga ráddjehus; bidde 0:s heaitti dihte dan.
max_tokenseaktodáhtolaš
Šládjainteger | null
1 – 6 144
Jiena-rámma ráhkadeami rájá, mas geavahuvvo modealla konteakstaráddjehus, jus eará maksima ii leat addojuvvon.
enable_safety_checkereaktodáhtolaš
Šládjaboolean
Standárdatrue
Gáhtten sáhttá loahpahuvvot bidjamiin false, jos geavaheaddji lea das ovttastuvvon.
gáibiduvvo

Fiilaparametterat váldet almmolaš https:// URL:a, data: URI:a gitta 10 MB, dahje uploada file_url:a. Fiillat

Boađus

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "zonos2",
  "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": 20,
    "usd": "0.02",
    "charged": 20,
    "refunded": 0
  },
  "input": {
    "reference_audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "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"
  }
}
Du fiillat, du válljenJuohke outputs[].url lea kopia min vurkemis: bisuhuvvo álo (mákso GB-mánu mielde) dahje 7 beaivvi nuvttá, du konto­o heiveheami dahje ?storage= mielde.
Seammá hápmi juohke modeallastype, url, content_type, width, height ja duration, govvii, videoii ja jienai seammá ládje. output lea modealla iežas boađusobjekta.
Outputa giettit
audio
object {url, content_type, file_name, file_size}Boađus-jietna WAV-formáhtas, 44.1kHz samplingfreavnnain ja mono-kanálain.
seed
integerRáhkadeamis geavahuvvon sádjiárvu.

AI-agenttaide: dán siidu Markdowna lea dáppe https://doitong.com/se/developers/models/zonos2.md. Buot modeallat ja ráđit: https://doitong.com/developers/llms.txt