Ruka hadi kwenye maudhui

OpenRouter [Audio]

Unganisha

Kitambulisho cha modeli openrouter/router/audio
# 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/openrouter/router/audio?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",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "model": "google/gemini-3.8-flash"
  }'

# 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 $ 1.858 kwa kila uendeshaji hutozwa kulingana na matumizi halisi, yaliyosalia yanarejeshwa Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
OpenRouter LLM

Toleo la lango la LLM linalochakata faili ya sauti kwa unukuzi au uchanganuzi, likiwa na kidokezo

OpenRouter · Maandishi

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

Kidokezo kinachoelekeza uchakataji wa sauti.

•inahitajika audio_url
Dondosha faili, au

Ingizo la sauti la kuchakatwa, lililotajwa kwa URL au URI ya data. Miundo inayokubaliwa ni m4a, flac, ogg, aac, aiff, mp3 na wav.

•inahitajika

Jina linalotambulisha modeli ya kuendesha.

Ya kina system_prompt · temperature · max_tokens · reasoning · enable_web_search · web_search_options

Kidokezo cha mfumo kinachotoa maelekezo au muktadha kwa modeli.

chaguomsingi 1

Udhibiti wa utofauti wa jibu, ambapo 0 huhakikisha jibu linalofanana kila ingizo linapokuwa bila kubadilika. Kuongeza thamani hupeleka majibu mbali na majibu yanayotabirika na ya kawaida kuelekea utofauti mkubwa na majibu yasiyo ya kawaida.

Weka kikomo cha idadi ya tokeni zinazozalishwa katika jibu kuwa thamani isiyozidi urefu wa muktadha ukitoa urefu wa kidokezo. Uzalishaji hauwezi kuzidi kikomo kilichobainishwa.

Usanidi wa utafutaji wa wavuti, ikijumuisha uteuzi wa injini, vikomo vya matokeo na uchujaji wa vikoa. Hutumika tu wakati enable_web_search ni true.

POST /run/openrouter/router/audio?wait=20 makadirio → $ 1.858
# 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/openrouter/router/audio?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",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "model": "google/gemini-3.8-flash"
  }'

# 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 OpenRouter [Audio]

Hupokea faili ya sauti kupitia `audio_url` pamoja na `prompt` na `model` inayohitajika. Miundo iliyoorodheshwa ni wav, mp3, aiff, aac, ogg, flac na m4a. `system_prompt`, `temperature`, `max_tokens`, `reasoning` na mipangilio ya utafutaji wa wavuti ya hiari inapatikana. Hurejesha matokeo ya maandishi na matumizi ya tokeni.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo
audio_urlinahitajika audio
Ainaurl · audio
Ingizo la sauti la kuchakatwa, lililotajwa kwa URL au URI ya data. Miundo inayokubaliwa ni m4a, flac, ogg, aac, aiff, mp3 na wav.
promptinahitajika
Ainastring
Kidokezo kinachoelekeza uchakataji wa sauti.
system_promptsi lazima
Ainastring | null
Kidokezo cha mfumo kinachotoa maelekezo au muktadha kwa modeli.
modelinahitajika
Ainastring
Jina linalotambulisha modeli ya kuendesha.
reasoningsi lazima
Ainaboolean
Chaguomsingifalse
Iwapo hoja zijumuishwe katika jibu la mwisho.
temperaturesi lazima
Ainanumber
Chaguomsingi1
0 – 2
Udhibiti wa utofauti wa jibu, ambapo 0 huhakikisha jibu linalofanana kila ingizo linapokuwa bila kubadilika. Kuongeza thamani hupeleka majibu mbali na majibu yanayotabirika na ya kawaida kuelekea utofauti mkubwa na majibu yasiyo ya kawaida.
max_tokenssi lazima
Ainainteger | null
≥ 1
Weka kikomo cha idadi ya tokeni zinazozalishwa katika jibu kuwa thamani isiyozidi urefu wa muktadha ukitoa urefu wa kidokezo. Uzalishaji hauwezi kuzidi kikomo kilichobainishwa.
web_search_optionssi lazima
Ainaobject
Usanidi wa utafutaji wa wavuti, ikijumuisha uteuzi wa injini, vikomo vya matokeo na uchujaji wa vikoa. Hutumika tu wakati enable_web_search ni true.
web_search_options.enginesi lazima
Ainaenum
Chaguomsingiauto
autonativeexa
Uteuzi wa injini ya utafutaji: 'auto' na 'native' zote hurudi Exa wakati utafutaji wa asili haupatikani. 'auto' hutumia utafutaji wa mtoa huduma wa asili unaopatikana; 'native' hupendelea utafutaji uliojengewa ndani kutoka OpenAI, Anthropic, Google, xAI au Perplexity. Ili kutumia API ya utafutaji ya Exa pekee, chagua 'exa'.
web_search_options.max_resultssi lazima
Ainainteger | null
1 – 25
Kikomo cha matokeo kwa kila mwito wa utafutaji wa Exa, kutoka 1 hadi 25, chaguomsingi ikiwa 5. Utafutaji wa mtoa huduma wa asili hupuuza mpangilio huu.
web_search_options.max_usessi lazima
Ainainteger | null
≥ 1
Kikomo cha utafutaji kwa kila ombi, kinachotumwa kwa Anthropic kwa utafutaji wa asili lakini kupuuzwa na watoa huduma wengine wa asili. Miito inayozidi kikomo hupokea tokeo la hitilafu na haiendeshwi.
web_search_options.max_total_resultssi lazima
Ainainteger | null
≥ 1
Kikomo cha pamoja cha matokeo kwa utafutaji wote ndani ya ombi moja.
web_search_options.search_context_sizesi lazima
Ainaenum
lowmediumhigh
Kiasi cha kurejesha kwa kila tokeo cha Exa, kinachobatilishwa na max_characters ikiwa vyote vimetolewa na kupuuzwa kwa utafutaji wa mtoa huduma wa asili. Chagua low kwa herufi 5K, medium kwa 15K au high kwa 30K; kutoainisha huiruhusu Exa kurekebisha kiasi hadi takriban 2–4K kwa kila tokeo.
web_search_options.max_characterssi lazima
Ainainteger | null
1 – 100,000
Kikomo cha herufi za maudhui kwa kila tokeo cha Exa, kinachobatilisha search_context_size ikiwa mipangilio yote imetolewa. Weka kiwango cha juu kamili kutoka herufi 1 hadi 100,000; utafutaji wa mtoa huduma wa asili hupuuza mpangilio huu.
web_search_options.allowed_domainssi lazima
Ainastring[]
Orodha ya vikoa vinavyoruhusiwa kwa Exa na watoa huduma wengi wa utafutaji wa asili, ikizuia matokeo kwenye vikoa vilivyoorodheshwa. Utafutaji wa asili wa Google hauiungi mkono.
web_search_options.excluded_domainssi lazima
Ainastring[]
Orodha ya kuondoa vikoa kwa utafutaji wa Exa na watoa huduma wa asili wanaooana; utafutaji wa asili wa Google na OpenAI hauwezi kutumia orodha hii. Matokeo yanayotoka kwenye vikoa vilivyoorodheshwa huondolewa.
web_search_options.user_locationsi lazima
Ainaobject
Eneo la karibu la mtumiaji linalopendelea kijiografia matokeo ya utafutaji wa asili; Exa haitumii maelezo haya.
web_search_options.user_location.typesi lazima
Ainastring
Chaguomsingiapproximate
Uainishaji wa eneo; thamani pekee inayotumika ni 'approximate'.
web_search_options.user_location.citysi lazima
Ainastring | null
Jina la jiji, kama vile 'San Francisco'.
web_search_options.user_location.regionsi lazima
Ainastring | null
Jina la jimbo au eneo, kama vile 'California'.
web_search_options.user_location.countrysi lazima
Ainastring | null
Kitambulisho cha nchi kilichoonyeshwa kwa herufi mbili, kama vile 'US'.
web_search_options.user_location.timezonesi lazima
Ainastring | null
Kitambulisho cha saa katika nukuu za IANA, kama vile 'America/Los_Angeles'.
inahitajika Jina rasmi, pia linakubalika

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": "openrouter/router/audio",
  "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": 1858,
    "usd": "1.858",
    "charged": 1858,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "model": "google/gemini-3.8-flash"
  },
  "output": {
    "output": "The audio contains a conversation between two people discussing the weather forecast for the upcoming week.",
    "usage": {
      "prompt_tokens": 1,
      "completion_tokens": 1,
      "total_tokens": 0,
      "cost": 1.0,
      "prompt_tokens_details": {
        "cached_tokens": 0,
        "cache_write_tokens": 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"
  }
}
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
output
stringTokeo lililozalishwa kwa kuchakata sauti.
usage
object {prompt_tokens, completion_tokens, total_tokens, cost, prompt_tokens_details} | nullMaelezo ya matumizi ya tokeni.

Miundo zaidi: LLM

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