Ruka hadi kwenye maudhui

Zonos2 Text to Speech

Unganisha

Kitambulisho cha modeli 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"

Hadi $ 0.02 kwa kila uendeshaji hutozwa kulingana na matumizi halisi, yaliyosalia yanarejeshwa Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Zyphra Maandishi hadi Matamshi Ingizo za marejeleo #text-to-speech#tts#voice-cloning

TTS ya kunakili sauti kwa lugha nyingi yenye vidhibiti vya usampulishaji na chaguo kati ya ulinganifu wa karibu au uwasilishaji wa kihisia

Zyphra · Sauti

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

•inahitajika
Dondosha faili, au

Sauti inayotoa sauti chanzo kwa ajili ya kunakili.

Ya kina language · temperature · top_p · min_p · top_k · max_tokens · seed · accurate_mode · clean_speaker_background · enable_safety_checker
chaguomsingi en_us

Uteuzi wa lugha kwa urekebishaji wa maandishi, ambao hurukwa isipokuwa msimbo uwe mojawapo ya: en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn, ko.

chaguomsingi 1.15

Joto linalotumika kwa sampuli.

chaguomsingi 0

Uwezekano wa sampuli ya nucleus; weka 0 ili kuizima.

chaguomsingi 0.18

Kizingiti cha uwezekano kwa sampuli ya uwezekano wa chini.

chaguomsingi 106

Kikomo cha sampuli ya top-k; weka 0 ili kuizima.

Kikomo cha uzalishaji wa fremu za sauti, kwa kutumia kikomo cha muktadha wa modeli isipokuwa kiwango cha juu kimetolewa.

Seed inayowezesha matokeo yanayoweza kurudiwa; huchaguliwa bila mpangilio isipojumuishwa.

POST /run/zonos2?wait=20 makadirio → $ 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"

Endesha ombi hili

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Pata ufunguo wa API

Kuhusu Zonos2 Text to Speech

Hunakili sauti kutoka kwa `reference_audio_url` na kutamka maandishi, ikirejesha sauti ya WAV ya 44.1kHz mono pamoja na mbegu iliyotumika. `language` huweka urekebishaji wa maandishi kwa en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn na ko. `accurate_mode` hubadilisha ukaribu wa sauti kwa uwasilishaji wa kihisia, na usampulishaji unaweza kurekebishwa kupitia `temperature`, `top_p`, `min_p`, `top_k` na `max_tokens` (hadi 6144).

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
reference_audio_urlinahitajika
Ainaurl · audio
Sauti inayotoa sauti chanzo kwa ajili ya kunakili.
languagesi lazima
Ainastring
Chaguomsingien_us
Uteuzi wa lugha kwa urekebishaji wa maandishi, ambao hurukwa isipokuwa msimbo uwe mojawapo ya: en_us, en_gb, fr_fr, de, es, it, pt_br, ja, cmn, ko.
seedsi lazima
Ainainteger | null
0 – 2,147,483,647
Seed inayowezesha matokeo yanayoweza kurudiwa; huchaguliwa bila mpangilio isipojumuishwa.
accurate_modesi lazima
Ainaboolean
Chaguomsingitrue
Ulinganishaji wa sauti dhidi ya uelezaji: True hupendelea ulinganishaji wa karibu zaidi, huku False ikipendelea matamshi yenye uelezaji zaidi.
clean_speaker_backgroundsi lazima
Ainaboolean
Chaguomsingifalse
Huonyesha kuwa sauti ya rejeleo ina mandharinyuma safi.
temperaturesi lazima
Ainanumber
Chaguomsingi1.15
0 – 2
Joto linalotumika kwa sampuli.
top_psi lazima
Ainanumber
Chaguomsingi0
0 – 1
Uwezekano wa sampuli ya nucleus; weka 0 ili kuizima.
min_psi lazima
Ainanumber
Chaguomsingi0.18
0 – 1
Kizingiti cha uwezekano kwa sampuli ya uwezekano wa chini.
top_ksi lazima
Ainainteger
Chaguomsingi106
0 – 2,048
Kikomo cha sampuli ya top-k; weka 0 ili kuizima.
max_tokenssi lazima
Ainainteger | null
1 – 6,144
Kikomo cha uzalishaji wa fremu za sauti, kwa kutumia kikomo cha muktadha wa modeli isipokuwa kiwango cha juu kimetolewa.
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.
inahitajika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

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"
  }
}
Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.
Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.
Sehemu za tokeo
audio
object {url, content_type, file_name, file_size}Tokeo la sauti katika umbizo la WAV, lenye sampuli ya 44.1kHz na chaneli ya mono.
seed
integerThamani ya seed inayotumika wakati wa uzalishaji.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/zonos2.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt