Ruka hadi kwenye maudhui

Eleven v4 Text to Speech

Unganisha

Kitambulisho cha modeli elevenlabs/tts/eleven-v4
# 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/elevenlabs/tts/eleven-v4?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "[whispers] Okay, everyone, gather close. [excited] The bread is finally out of the oven. [laughs] Fine, fine, one slice each, but only if you promise to save one for me."
  }'

# 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"

Ombi hili: $ 0.014 salio za API 14 · ≈ ₽ 1.51 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
ElevenLabs Maandishi hadi Matamshi #voiceover#expressive#timestamps

Muundo wa sauti wa ElevenLabs wenye uelezaji wa hisia zaidi, ukiwa na tagi za hisia ndani ya maandishi na mihuri ya muda kwa kila neno.

Mifano

Tokeo · ~14 s
[whispers] Okay, everyone, gather close. [excited] The bread is finally out of the oven. [laughs] Fine, fine, one slice each, but only if you promise to save one for me.$ 0.014 · salio za API 14

Unda ombi

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

•inahitajika 169 / 5000

Toa maudhui ya matamshi kama maandishi, ukitia alama hiari za uwasilishaji kwa tagi za sauti kama vile [whispering] au kubainisha matamshi ya IPA kati ya mistari ya mbele.

chaguomsingi Rachel

Sauti iliyochaguliwa kwa usanisi wa matamshi.

Ya kina apply_text_normalization · language_code · output_format · stability · similarity_boost · seed · timestamps
apply_text_normalization chaguomsingi auto

Hudhibiti urekebishaji wa maandishi kabla ya uzalishaji, ikijumuisha ushughulikiaji wa nambari na tarehe.

Msimbo wa lugha wa ISO 639-1 unaotumiwa wakati wa kuzalisha matamshi na kurekebisha maandishi.

chaguomsingi mp3_44100_128

Umbizo la sauti iliyotengenezwa, lililobainishwa kwa muundo wa codec_sample_rate_bitrate.

chaguomsingi 0.5

Uthabiti wa sauti husawazisha uwasilishaji wa kimtindo katika mipangilio ya chini dhidi ya uwasilishaji thabiti katika mipangilio ya juu.

chaguomsingi 0.75

Udhibiti wa ufanano wa sauti-rejeleo, wenye uwezekano wa kubadilishana na uasilia: kuiongeza huimarisha ulinganifu lakini kunaweza kufanya tokeo lisikike si la asili.

Seed inayotumiwa kujaribu kupata matokeo yanayoweza kurudiwa; kurudiwa kwa tokeo kamili hakuhakikishwi.

POST /run/elevenlabs/tts/eleven-v4?wait=20 makadirio → $ 0.014
# 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/elevenlabs/tts/eleven-v4?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "[whispers] Okay, everyone, gather close. [excited] The bread is finally out of the oven. [laughs] Fine, fine, one slice each, but only if you promise to save one for me."
  }'

# 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"

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 Eleven v4 Text to Speech

Eleven v4 husoma maandishi kwa sauti za asili zenye hisia na huelewa tagi za sauti ndani ya maandishi kama [excited] au [whispering], pamoja na matamshi ya IPA. Chagua sauti, rekebisha uthabiti na ufanano, weka lugha, na upate kwa hiari mihuri ya muda kwa kila neno. Miundo ya MP3, PCM, Opus na simu.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
textinahitajika
Ainastring
≤ herufi 5,000
Toa maudhui ya matamshi kama maandishi, ukitia alama hiari za uwasilishaji kwa tagi za sauti kama vile [whispering] au kubainisha matamshi ya IPA kati ya mistari ya mbele.
voicesi lazima
Ainastring
ChaguomsingiRachel
Sauti iliyochaguliwa kwa usanisi wa matamshi.
stabilitysi lazima
Ainanumber
Chaguomsingi0.5
0 – 1
Uthabiti wa sauti husawazisha uwasilishaji wa kimtindo katika mipangilio ya chini dhidi ya uwasilishaji thabiti katika mipangilio ya juu.
similarity_boostsi lazima
Ainanumber
Chaguomsingi0.75
0 – 1
Udhibiti wa ufanano wa sauti-rejeleo, wenye uwezekano wa kubadilishana na uasilia: kuiongeza huimarisha ulinganifu lakini kunaweza kufanya tokeo lisikike si la asili.
seedsi lazima
Ainainteger | null
0 – 4,294,967,295
Seed inayotumiwa kujaribu kupata matokeo yanayoweza kurudiwa; kurudiwa kwa tokeo kamili hakuhakikishwi.
language_codesi lazima
Ainastring | null
Msimbo wa lugha wa ISO 639-1 unaotumiwa wakati wa kuzalisha matamshi na kurekebisha maandishi.
output_formatsi lazima
Ainaenum
Chaguomsingimp3_44100_128
mp3_22050_32mp3_44100_32mp3_44100_64mp3_44100_96mp3_44100_128mp3_44100_192pcm_8000pcm_16000pcm_22050pcm_24000pcm_44100pcm_48000ulaw_8000alaw_8000opus_48000_32opus_48000_64
+3 zaidiopus_48000_96opus_48000_128opus_48000_192
Umbizo la sauti iliyotengenezwa, lililobainishwa kwa muundo wa codec_sample_rate_bitrate.
apply_text_normalizationsi lazima
Ainaenum
Chaguomsingiauto
autoonoff
Hudhibiti urekebishaji wa maandishi kabla ya uzalishaji, ikijumuisha ushughulikiaji wa nambari na tarehe.
timestampssi lazima
Ainaboolean
Chaguomsingifalse
Hudhibiti ikiwa sauti inayozalishwa inaambatana na data ya muda kwa herufi mahususi.
inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "elevenlabs/tts/eleven-v4",
  "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": 14,
    "usd": "0.014",
    "charged": 14,
    "refunded": 0
  },
  "input": {
    "text": "[excited] Hello! Welcome to the future of voice.",
    "voice": "Aria"
  },
  "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
    },
    "timestamps": []
  },
  "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"
  }
}
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}Faili ya sauti iliyotengenezwa kupitia uzalishaji.
timestamps
array of any | nullData ya muda wa usemi uliotengenezwa, inayojumuishwa tu kwa maombi yenye `timestamps` iliyowekwa True, ikiwa na muhuri wa muda kwa kila neno.

Miundo zaidi: Maandishi hadi Matamshi

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/elevenlabs/tts/eleven-v4.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt