Dža ko lil

Chatterboxhd · Text to Speech

Integriruj

Modelosko id resemble-ai/chatterboxhd/text-to-speech
# 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/resemble-ai/chatterboxhd/text-to-speech?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

# 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"

Fajlo sar o misalo: $0.011 11 API krediti · ≈ ₽1.18 tire fajlo si merime angl-o phiripen Phir les kate

Lel API klidin
Resemble AI Teksto ko Lav

Expressive text-to-speech preset voices-enca, zero-shot cloning katar sample thaj opcionalno 48 kHz audio

Resemble AI · Audio

Tiro prvo rezultato si kate

Ker tele jekh mangipen thaj phir les tire API klidinosa. E rezultatur si kopirime amare arakhipneste, vično vaj 7 dives bilačhes.

Ker jekh mangipen

O kontrolura kerde si katar e schemaske. O kodo thaj e cena menjinen sar tu len menjines.

standardno My name is Maximus De...

Tekstosko sadržaj savo konvertirinel pes ande lavutno audio.

Lučhe audio · voice · exaggeration · cfg · temperature · seed · high_quality_audio
audio_url
Čhiv jekh fajl, vaj

URL e voćakere kloniripaskoro sample vaš zero-shot TTS, savo lel prioritetos k voćakoro setting. Random voćakoro alosaripen aplicar pes numa kana na si ni audio_url ni voice.

Alosar e TTS voća, vaj na thov ni voća ni audio te mukhel e sistemos te alosarel jek random.

standardno 0.5

Gono e emocijakoro bararipasko, normalno maškar 0.25 thaj 2.0.

standardno 0.5

Zor e conditioning-i savi setuil pes e classifier-free guidance (CFG-eça). Ekspresivno vaj dramatikano lavutnaskere rezultatura, phand cikno cfg setting, sar približno 0.3, e bararipasha približno 0.7 vaj maj but; cikneder cfg k približno 0.3 šaj te lačharel vi e ritmos kana referentno voća vakerel sigo. Tipično settinga si 0.2–1.0.

standardno 0.8

Randomnost e keripaski, normalno maškar 0.05 thaj 5.

standardno 0

Seed vaš repetabilno audio keripe: 0 alosarel jek random, a fixno seed trubul te kerel isto audio fajlo te savorre aver svojstva ačhen jekh.

POST /run/resemble-ai/chatterboxhd/text-to-speech?wait=20 hesab → $0.011
# 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/resemble-ai/chatterboxhd/text-to-speech?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'

# 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"

Phandel kava mangipen

Tiro kluč ačhel kadale browsereste: bičhalel pes numa ko Doitong API thaj šuvav pes (localStorage) numa te tiknes Remember. Le jekh API ključ

Palal Chatterboxhd · Text to Speech

Generirrel vakeripe katar `text`, preset `voice`-esa (Aurora, Blade, Britney, Carl, Cliff, Richard, Rico, Siobhan or Vicky) vaj klonime glaso katar `audio_url`, savo override-kerel o preset. `exaggeration` (0.25 to 2) thaj `cfg` kontrolinena emocija, thaj `temperature` thaj `seed` kontrolinena varijacija. `high_quality_audio` barjarel o avrutno katar 24 kHz ko 48 kHz.

Parametra

Bičhalav vaj e kanonikano nav vaj e native nav, na duj. Kanonikane nava

NavTip standardnoMuklo Vakeripe
textopcionalno
Tipstring
standardnoMy name is Maximus Decimus Meridius, commander of the Armies of the North, General of the Felix Legions and loyal servant to the true emperor, Marcus Aurelius. Father to a murdered son, husband to a murdered wife. And I will have my vengeance, in this life or the next.
Tekstosko sadržaj savo konvertirinel pes ande lavutno audio.
voiceopcionalno
Tipenum
AuroraBladeBritneyCarlCliffRichardRicoSiobhanVicky
Alosar e TTS voća, vaj na thov ni voća ni audio te mukhel e sistemos te alosarel jek random.
audio_urlopcionalno audio
Tipurl · audio
URL e voćakere kloniripaskoro sample vaš zero-shot TTS, savo lel prioritetos k voćakoro setting. Random voćakoro alosaripen aplicar pes numa kana na si ni audio_url ni voice.
exaggerationopcionalno
Tipnumber
standardno0.5
0.25 – 2
Gono e emocijakoro bararipasko, normalno maškar 0.25 thaj 2.0.
cfgopcionalno
Tipnumber
standardno0.5
0 – 1
Zor e conditioning-i savi setuil pes e classifier-free guidance (CFG-eça). Ekspresivno vaj dramatikano lavutnaskere rezultatura, phand cikno cfg setting, sar približno 0.3, e bararipasha približno 0.7 vaj maj but; cikneder cfg k približno 0.3 šaj te lačharel vi e ritmos kana referentno voća vakerel sigo. Tipično settinga si 0.2–1.0.
high_quality_audioopcionalno
Tipboolean
standardnofalse
Alosar maškar 24kHz rezultato e False-eça thaj maj lačho audio upscalime k 48kHz e True-eça. Upscaling bararel e keripaskoro vaxto.
seedopcionalno
Tipinteger
standardno0
≥ 0
Seed vaš repetabilno audio keripe: 0 alosarel jek random, a fixno seed trubul te kerel isto audio fajlo te savorre aver svojstva ačhen jekh.
temperatureopcionalno
Tipnumber
standardno0.8
0.05 – 5
Randomnost e keripaski, normalno maškar 0.05 thaj 5.
trubul Kanonikano nav, vi akceptime

Fajloske parametra lel jekh publikano https:// URL, jekh data: URI dži 10 MB, vaj e file_url uploadoski. Fajlura

Rezultato

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "resemble-ai/chatterboxhd/text-to-speech",
  "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": 11,
    "usd": "0.011",
    "charged": 11,
    "refunded": 0
  },
  "input": {},
  "output": {},
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Tire fajlura, tiro alosaripenSako outputs[].url si kopija amare arakhipneste: vično (čargeime per GB-mase) vaj 7 dives bilačhes, tiro kontoskere regulaciatar vaj ?storage=.
Sa jekh forma sako modeloθartype, url, content_type, width, height thaj duration, varesave imajinake, video thaj audio-ke. output si o modelosko korkoro resultosko objekto.
Outputoske fieldura
audio
anyAudio-fajlo kerdino generiripeça.

Bute modeli: Teksto ko Lav

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/resemble-ai/chatterboxhd/text-to-speech.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt