Dža ko lil

Seed Audio 1.0

Integriruj

Modelosko id bytedance/seed-audio-1.0
# 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/bytedance/seed-audio-1.0?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Dži $0.154 pe jekh keripe čargeime palal realno labaripen, o aver si irime Phir les kate

Lel API klidin
ByteDance Audio

Generatoro lavutnesko thaj audiosko, textosa, dži ko 3 referenciako audio klip vaj jekh fotografia, pitch thaj speed kontroleça

ByteDance · 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.

•trubul 88 / 2048

Prompto vaj teksto sintezakero, audio referencenca ande redosari sikavde sar @Audio1 pala angluno inputo, @Audio2 pala dujto thaj @Audio3 pala trito.

standardno 1

Vakeripasko rate multiplier: 1.0 si normalno sigal, 0.5 si jekhpaš sigal, thaj 2.0 si dujvar sigal.

Lučhe audios · image · output_format · sample_rate · voice · volume · pitch · multilingual · enable_safety_checker
audio_urls
Čhiv jekh fajl, vaj · dži 3

Dien reference audio dži 3 URL-endar; sako fajlo wav/mp3/pcm/ogg_opus formatosa, limitime 10 MB thaj 30 sekunde. And-o prompto, identifikirin klipi sar @Audio1, @Audio2, @Audio3.

image_url
Čhiv jekh fajl, vaj

Dien jekh kipo reference URL-e numa kana na si audio reference. Kipo musaj te avel jpeg/png/webp thaj na baro sar 10 MB.

output_format standardno mp3

Formato pala kerde audio.

sample_rate standardno 24000

Sampling frekvencija ande Hz pala rezultato audio.

Alosar sintezakero glaso diena lesqo preset-nav vaj, klonime glaseske, lesqo ID.

standardno 1

Volume multiplier: 1.0 si normalno volume, 0.5 si jekhpaš, thaj 2.0 si dujvar baro volume.

standardno 0

Glasesko pitch sasajimos ande semitone: 0 mukel pitch bizo paruvimos, -12 lel les tele jekh oktava, thaj 12 lel les opre jekh oktava.

POST /run/bytedance/seed-audio-1.0?wait=20 hesab → $0.154
# 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/bytedance/seed-audio-1.0?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "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.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 Seed Audio 1.0

Sintetizirinel audio andar jekh prompto dži 2048 karakterura. Šaj te alosarel preset vaj klonime `voice`, thaj dži 3 referencijalne klipura šaj te citirinen andro prompto sar @Audio1 dži @Audio3; jekh referencijalno kipo šaj te avel lesko than, numa na jekhetane audio-esa. O rezultato si wav, mp3, pcm vaj ogg_opus e sample-rate-enca andar 8000 dži 48000 Hz. E brzina thaj volumino si andar 0.5 dži 2, pitch paruvlel -12 dži 12 semitona, thaj `multilingual` paruvlel ko varijanto pala mišime čhibaki teksto.

Parametra

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

NavTip standardnoMuklo Vakeripe
prompttrubul
Tipstring
≤ 2,048 simbolura
Prompto vaj teksto sintezakero, audio referencenca ande redosari sikavde sar @Audio1 pala angluno inputo, @Audio2 pala dujto thaj @Audio3 pala trito.
voiceopcionalno
Tipstring | null
Alosar sintezakero glaso diena lesqo preset-nav vaj, klonime glaseske, lesqo ID.
audio_urlsopcionalno audios
Tipurl[] · audio
≤ 3 artiklura
Dien reference audio dži 3 URL-endar; sako fajlo wav/mp3/pcm/ogg_opus formatosa, limitime 10 MB thaj 30 sekunde. And-o prompto, identifikirin klipi sar @Audio1, @Audio2, @Audio3.
image_urlopcionalno image
Tipurl · image
Dien jekh kipo reference URL-e numa kana na si audio reference. Kipo musaj te avel jpeg/png/webp thaj na baro sar 10 MB.
output_formatopcionalno
Tipenum
standardnomp3
wavmp3pcmogg_opus
Formato pala kerde audio.
sample_rateopcionalno
Tipenum
standardno24000
80001600024000320004410048000
Sampling frekvencija ande Hz pala rezultato audio.
speedopcionalno
Tipnumber
standardno1
0.5 – 2
Vakeripasko rate multiplier: 1.0 si normalno sigal, 0.5 si jekhpaš sigal, thaj 2.0 si dujvar sigal.
volumeopcionalno
Tipnumber
standardno1
0.5 – 2
Volume multiplier: 1.0 si normalno volume, 0.5 si jekhpaš, thaj 2.0 si dujvar baro volume.
pitchopcionalno
Tipinteger
standardno0
-12 – 12
Glasesko pitch sasajimos ande semitone: 0 mukel pitch bizo paruvimos, -12 lel les tele jekh oktava, thaj 12 lel les opre jekh oktava.
multilingualopcionalno
Tipboolean
standardnofalse
Alosar modelosa variant: multilingual variant federi kerel kana promptora misinel čhiben vaj si aver čhib sar English.
enable_safety_checkeropcionalno
Tipboolean
standardnotrue
Screening šaj te avel relaksirime te postavil pes false, numa kana o manglo si autorizuime.
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": "bytedance/seed-audio-1.0",
  "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": 154,
    "usd": "0.154",
    "charged": 154,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "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,
      "duration": 5,
      "channels": 1,
      "sample_rate": 1,
      "bitrate": "string"
    }
  },
  "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
object {url, content_type, file_name, file_size, duration, channels, sample_rate, bitrate}Audio-fajlo kerdino generiripeça.

AI agentenge: kadija rig sar Markdown si kate https://doitong.com/rom/developers/models/bytedance/seed-audio-1.0.md. Sa e modelura thaj e gidura: https://doitong.com/developers/llms.txt