NeuronAIʼdan AI assistentlar orqali foydalaning
Nutq yaratish, ovozlarni klonlash va audioni matnga aylantirish uchun Claude, ChatGPT, Codex va boshqa assistentlarni ulang.
Nimalar qila oladi
NeuronAI MCP serveri AI assistentga chatdan chiqmasdan NeuronAI hisobingiz bilan nutq yaratish, bir nechta ovozli dialoglar tuzish, ovozlarni klonlash va audioni matnga aylantirish imkonini beradi.
U Streamable HTTP orqali ishlaydi. Ilovalar brauzerda NeuronAI orqali kiradi, skriptlar esa API kalit yuboradi.
Har bir chaqiruv APIʼga yuborilgan xuddi shunday soʻrov kabi tekshiriladi, cheklanadi va toʻlanadi: kalit ruxsatlari, mahsulot limitlari va narxlar bir xil, toʻlov esa tashkilotingiz balansidan yechiladi. Sarf chaqiruvni amalga oshirgan kalit yoki ulangan ilova boʻyicha koʻrinadi.
U brauzer, kompyuter va telefondagi Claude, ChatGPT, Grok, Claude Code, Codex va Gemini CLI bilan, shuningdek Streamable HTTPʼni qoʻllaydigan har qanday boshqa mijoz bilan ishlaydi.
Shunday soʻrab koʻring
- «Oʻzbekcha ovozlarni koʻrsat.»
- «Bu xatboshini Saodat ovozida oʻqib ber.»
- «~/Downloads/meeting.mp3 faylini matnga aylantir.»
Aksariyat assistentlar kredit sarflaydigan yoki biror narsani oʻzgartiradigan vositani ishga tushirishdan oldin sizdan tasdiq soʻraydi. Claude va ChatGPTʼda kompyuteringizdagi fayl oʻrniga yozuvga havola bering.
Ulash
Assistentingizni tanlang va uning qadamlarini bajaring. Aksariyati brauzerda NeuronAI orqali kiradi, CLIʼlar esa buning oʻrniga API kalit yuborishi mumkin.
NeuronAI orqali kirish
Birinchi marta ilova brauzerda NeuronAI sahifasini ochadi. Kerak boʻlsa, tizimga kiring, ilova kreditlarini sarflaydigan tashkilotni tanlang va «Ruxsat berish» tugmasini bosing. Sahifada ilova nomi va sizni qaytaradigan manzil koʻrsatiladi. Ilova nomini oʻzi tanlaydi, shuning uchun manzilga ishoning.
Ilova faqat shu tashkilot bilan ishlaydi. Uni boshqa tashkilot bilan ishlatish uchun uzing va qaytadan ulang.
Claude ilovasida Customize boʻlimini oching, soʻng Connectors va Add custom connector bandini tanlang.
Server manzilini qoʻying, soʻng Add va Connect tugmalarini bosing.
URLNeuronAI hisobingizga kiring, tashkilotni tanlang va ruxsat bering.
Ulanganini tekshiring
Claude orqali oʻzbekcha ovozlar roʻyxatini soʻrang. Roʻyxat chiqsa, hammasi ishlaydi.
Agar Claude roʻyxatdan oʻtish usulini soʻrasa, Register automatically bandini tanlang.
Har bir yorliq ulanganini tekshirish usuli bilan tugaydi. Ulangan barcha ilovalar «Dasturchilar», keyin «MCP» boʻlimida koʻrinadi, ularni oʻsha yerda uzish mumkin.
API kalit orqali kirish
Skriptlar, CI va brauzer orqali kira olmaydigan mijozlar uchun buning oʻrniga API kalitni Authorization: Bearer sarlavhasida yuboring.
Kalitga barcha vositalar uchun yetarli boʻlgan tts:write, voices:write va stt:write ruxsatlarini hamda oylik sarf limitini bering.
«Dasturchilar», keyin «MCP» boʻlimini oching, CLI yorligʻiga oʻting va «Kirish usuli» maydonida «API kalit» variantini tanlang: u yerdagi «MCP uchun kalit yaratish» tugmasi shu ruxsatlar bilan kalit yaratadi, sarf limitini esa oʻsha shaklda belgilang.
Yuqoridagi CLI yorliqlarida kalit yuboradigan buyruqlarni koʻrish uchun «Kirish usuli» maydonida «API kalit» variantini tanlang; Grok Build buyrugʻi «Boshqa» yorligʻida. Mijoz kalitni muhitdan oʻqiy olsa, uning sozlamalarida faqat oʻzgaruvchi nomi, NEURONAI_API_KEY, saqlanadi. Claude Code bundan mustasno: uning buyrugʻi kalitning oʻzini ~/.claude.json faylida saqlaydi, shuning uchun imkon boʻlsa, Claude Codeʼga brauzer orqali kiring. Kalit yozilgan qator, jumladan export, shell tarixida qoladi.
PowerShellʼda oʻzgaruvchini export oʻrniga $env:NEURONAI_API_KEY = "nai_your_api_key" bilan belgilang.
Kalitni, uning limitlari va sarfini «Dasturchilar», keyin «API kalitlar» boʻlimida boshqaring.
Vositalar
Assistent har bir vositaning nomi, tavsifi va parametrlarini oʻqiydi va qaysi birini chaqirishni oʻzi hal qiladi. Bu yerda ular assistent oʻqiydigan koʻrinishda keltirilgan: ingliz tilida va server beradigan tartibda.
Assistent faqat kaliti yoki ulanishi chaqira oladigan vositalarni koʻradi. Har bir natijada request_id boʻladi: qoʻllab-quvvatlash xizmatiga yozganda uni koʻrsating.
list_voices
Siz foydalana oladigan ovozlarni koʻrsatadi.
- Ruxsat
- Ruxsat kerak emas
- Narx
- Bepul
Assistent nimani oʻqiydi
Lists the voices you can speak with: NeuronAI's stock voices first, in catalog order, then the organization's own voice clones, newest first, when the API key may read voices. Filter with type (stock or custom) and language (a code such as uz, ru or en). A page holds up to limit voices (1 to 100, default 50); while next_cursor is not null, call again with it as cursor for the next page. Pass a voice's id as voice_id to text_to_speech or text_to_dialogue. Free.Parametrlar
| Parametr | Tavsif |
|---|---|
typestring | Only stock voices, or only the organization's voice clones. Omit for both. Ruxsat etilgan qiymatlar: |
languagestring | Only voices in this language, as a code such as uz, ru or en. maxLen: 16 |
limitinteger | How many voices one page holds. min: 1 · max: 100 · default: 50 |
cursorstring | The next_cursor of the previous page. maxLen: 512 |
Natija
| Maydon | Tavsif |
|---|---|
voicesobject[] | |
voices[]string | Pass it as voice_id. |
voices[]string | |
voices[]string | |
voices[]string[] | |
voices[]string | Ruxsat etilgan qiymatlar: |
voices[]string | Voice clones only. |
voices[]string | null | Voice clones only: what the reference clip says. |
voices[]string | null | Voice clones only. |
next_string | null | Pass it as cursor for the next page; null on the last page. |
request_string |
text_to_speech
Matnni nutqqa aylantiradi va audio havolasini qaytaradi.
- Ruxsat
tts:write- Narx
- Har bir belgi uchun 0,3 kredit, ovoz kloni bilan 0,5 kredit
Assistent nimani oʻqiydi
Turns text into speech and returns a link to the audio file, Opus unless format names mp3 or wav. Choose voice_id with list_voices: a stock voice or one of the organization's voice clones. text holds up to 10000 characters, counted as spoken: an emotion tag counts as one. Emotion tags are directions the voice acts out rather than reads: [laughter], [sigh], [dissatisfaction-hnn], [confirmation-en], [question-en], [question-ah], [question-oh], [question-ei], [question-yi], [surprise-ah], [surprise-oh], [surprise-wa], [surprise-yo]. The tool waits up to 40 seconds for the audio. If it is not ready by then, the answer has status queued or running and a job_id: call get_speech with that job_id after about 15 seconds. An identical call within 10 minutes returns the latest result and charges nothing; pass new_take: true only when the user wants a different take. If a call with new_take: true got no answer, repeat it without new_take: that returns the take it made instead of paying for another.
This spends credits from the organization's balance: 0.3 credits per character with a stock voice, 0.5 with a voice clone. Call it only when the user asks, and never call it again to retry a call that succeeded.Parametrlar
| Parametr | Tavsif |
|---|---|
textstringMajburiy | The words to speak, up to 10000 characters counted as spoken. minLen: 1 |
voice_string | A voice id from list_voices: a stock voice or one of the organization's voice clones. maxLen: 128 |
languagestring | The language the text is written in. Ruxsat etilgan qiymatlar: |
qualitystring | fast is quickest, high sounds best; standard is the default. Ruxsat etilgan qiymatlar: |
speednumber | How fast the voice speaks: 1 is normal, from 0.5 to 2. min: 0.5 · max: 2 |
formatstring | The audio file's format: opus (the default, and the smallest), mp3 or wav (the largest). Ruxsat etilgan qiymatlar: |
new_boolean | true makes a fresh take of an identical call from the last few minutes, and charges for it. Leave it out otherwise. |
Natija
| Maydon | Tavsif |
|---|---|
statusstring | succeeded: the audio is ready. queued or running: call get_speech with job_id after retry_after_seconds. Ruxsat etilgan qiymatlar: |
job_string | The speech job, for get_speech. |
audioobject | The audio, as a link and as an MCP resource. Set when status is succeeded. |
audio.string | A link to the audio file. Anyone with the link can play it until expires_at, so give it only to the user. |
audio.string | When the link stops working: at most 24 hours from now. |
audio.string | The same audio as an MCP resource, for a client that cannot open the link: read it with resources/read. Free, up to 40 MB. |
audio.string | opus, mp3 or wav. Ruxsat etilgan qiymatlar: |
character_integer | Characters billed; an emotion tag counts as one. Set when status is succeeded. |
costnumber | Credits charged. Set when status is succeeded. |
balancenumber | The organization's balance in credits after the charge. Set when status is succeeded. |
retry_integer | Set while status is queued or running: wait this long, then call get_speech. |
replayedboolean | true when this repeats an identical call from the last few minutes, which charged nothing more. |
request_string | This call's request id, for support. |
get_speech
Nutq vazifasini tekshiradi va audio tayyor boʻlganda havolasini qaytaradi.
- Ruxsat
tts:read- Narx
- Bepul
Assistent nimani oʻqiydi
Checks a speech job that text_to_speech answered with status queued or running, and returns the link to its audio once it is ready. If it is still not ready, call get_speech again after about 15 seconds. It is free, and it never starts a new job.Parametrlar
| Parametr | Tavsif |
|---|---|
job_stringMajburiy | The job_id text_to_speech answered with. minLen: 26 · maxLen: 26 |
Natija
| Maydon | Tavsif |
|---|---|
statusstring | succeeded: the audio is ready. queued or running: call get_speech with job_id after retry_after_seconds. Ruxsat etilgan qiymatlar: |
job_string | The speech job, for get_speech. |
audioobject | The audio, as a link and as an MCP resource. Set when status is succeeded. |
audio.string | A link to the audio file. Anyone with the link can play it until expires_at, so give it only to the user. |
audio.string | When the link stops working: at most 24 hours from now. |
audio.string | The same audio as an MCP resource, for a client that cannot open the link: read it with resources/read. Free, up to 40 MB. |
audio.string | opus, mp3 or wav. Ruxsat etilgan qiymatlar: |
character_integer | Characters billed; an emotion tag counts as one. Set when status is succeeded. |
costnumber | Credits charged. Set when status is succeeded. |
balancenumber | The organization's balance in credits after the charge. Set when status is succeeded. |
retry_integer | Set while status is queued or running: wait this long, then call get_speech. |
replayedboolean | true when this repeats an identical call from the last few minutes, which charged nothing more. |
request_string | This call's request id, for support. |
text_to_dialogue
Bir nechta replikani turli ovozlarda bitta yozuvga aylantiradi.
- Ruxsat
tts:write- Narx
- Har bir belgi uchun 0,3 kredit, ovoz kloni bilan 0,5 kredit
Assistent nimani oʻqiydi
Speaks a script of several lines, each in its own voice, as one recording, and returns a link to it with where each line starts and ends. The recording is Opus unless format names mp3 or wav. turns holds 1 to 100 lines: each has a voice_id from list_voices and its text, and may set its own language, quality and speed; the top-level language, quality and speed apply to every line that sets none. gap_ms is the silence between lines, from 0 to 5000. The whole script holds up to 10000 characters, counted as spoken: an emotion tag counts as one. Emotion tags are directions the voice acts out rather than reads: [laughter], [sigh], [dissatisfaction-hnn], [confirmation-en], [question-en], [question-ah], [question-oh], [question-ei], [question-yi], [surprise-ah], [surprise-oh], [surprise-wa], [surprise-yo]. A long script can take a minute or two. Each line is billed at its own voice's rate. An identical call within 10 minutes returns the latest result and charges nothing; pass new_take: true only when the user wants a different take. If a call with new_take: true got no answer, repeat it without new_take: that returns the take it made instead of paying for another.
This spends credits from the organization's balance: 0.3 credits per character with a stock voice, 0.5 with a voice clone. Call it only when the user asks, and never call it again to retry a call that succeeded.Parametrlar
| Parametr | Tavsif |
|---|---|
turnsobject[]Majburiy | The script, line by line: 1 to 100 lines. minItems: 1 · maxItems: 100 |
turns[]stringMajburiy | A voice id from list_voices. maxLen: 128 |
turns[]stringMajburiy | What this voice says. minLen: 1 |
turns[]string | The language the text is written in. Ruxsat etilgan qiymatlar: |
turns[]string | fast is quickest, high sounds best; standard is the default. Ruxsat etilgan qiymatlar: |
turns[]number | How fast the voice speaks: 1 is normal, from 0.5 to 2. min: 0.5 · max: 2 |
languagestring | The language the text is written in. Ruxsat etilgan qiymatlar: |
qualitystring | fast is quickest, high sounds best; standard is the default. Ruxsat etilgan qiymatlar: |
speednumber | How fast the voice speaks: 1 is normal, from 0.5 to 2. min: 0.5 · max: 2 |
gap_integer | Silence between lines, in milliseconds. min: 0 · max: 5000 |
formatstring | The audio file's format: opus (the default, and the smallest), mp3 or wav (the largest). Ruxsat etilgan qiymatlar: |
new_boolean | true makes a fresh take of an identical call from the last few minutes, and charges for it. Leave it out otherwise. |
Natija
| Maydon | Tavsif |
|---|---|
audioobject | The audio, as a link and as an MCP resource. |
audio.string | A link to the audio file. Anyone with the link can play it until expires_at, so give it only to the user. |
audio.string | When the link stops working: at most 24 hours from now. |
audio.string | The same audio as an MCP resource, for a client that cannot open the link: read it with resources/read. Free, up to 40 MB. |
audio.string | opus, mp3 or wav. Ruxsat etilgan qiymatlar: |
turnsobject[] | Where each line is in the recording, in seconds, so a player can seek to it. |
turns[]integer | |
turns[]string | |
turns[]number | |
turns[]number | |
turns[]number | |
character_integer | Characters billed; an emotion tag counts as one. |
costnumber | Credits charged. |
balancenumber | The organization's balance in credits after the charge. |
replayedboolean | true when this repeats an identical call from the last few minutes, which charged nothing more. |
request_string | This call's request id, for support. |
create_upload
Terminaldagi assistentga kompyuteringizdan audio fayl yuklash uchun havola beradi.
- Ruxsat
stt:writeyokivoices:write- Narx
- Bepul
Assistent nimani oʻqiydi
Creates a short-lived link to upload an audio file from the user's computer. Purpose transcription is for speech_to_text (mp3, wav, ogg, flac, m4a, webm, up to 25 MB); purpose voice_sample is for clone_voice (wav, mp3, ogg, flac, up to 10 MB). Run the curl command it returns in the user's shell, with the file's path in place of ./FILE, then pass the upload_id to that tool. On Windows, run curl.exe (PowerShell's curl is a different command). The link works for 60 minutes. Without a shell, ask the user for a link to the recording instead and pass it to speech_to_text as audio_url. A voice sample needs a shell to run the curl command, because clone_voice takes no audio_url.Parametrlar
| Parametr | Tavsif |
|---|---|
purposestringMajburiy | transcription for speech_to_text, voice_sample for clone_voice. Ruxsat etilgan qiymatlar: |
Natija
| Maydon | Tavsif |
|---|---|
upload_string | Pass it to the tool the upload is for, once the file is uploaded. |
upload_string | Where to PUT the file. Signed: it is the only credential. |
methodstring | Ruxsat etilgan qiymatlar: |
expires_string | When the link, and the upload, stop working. |
max_integer | The largest file the link takes. |
formatsstring[] | The formats the file may be. |
curlstring | The command that uploads the file, with ./FILE to replace by its path. |
request_string | This call's request id, for support. |
speech_to_text
Havoladagi yoki yuklangan yozuvni matnga aylantiradi.
- Ruxsat
stt:write- Narx
- Audioning har bir soniyasi uchun 1 kredit
Assistent nimani oʻqiydi
Transcribes a recording to text. Pass exactly one of upload_id or audio_url: upload_id comes from create_upload with purpose transcription, for a file on the user's computer; audio_url is a public https link to the recording, followed through at most 3 redirects. Formats: mp3, wav, ogg, flac, m4a, webm, up to 25 MB. language is one of uz, kaa, ru, en, kk, tk, tg, tr, az, ja, de, ko, or auto (the default) to detect it. Set include_segments to also get the text in timed segments. An identical call within 10 minutes returns the latest result and charges nothing; pass new_take: true only when the user wants a fresh transcription. If a call with new_take: true got no answer, repeat it without new_take: that returns the take it made instead of paying for another.
This spends credits from the organization's balance: 1 credit per second of audio. Call it only when the user asks, and never call it again to retry a call that succeeded.Parametrlar
| Parametr | Tavsif |
|---|---|
upload_string | The upload_id from create_upload with purpose transcription, once the file is uploaded. Pass this or audio_url. maxLen: 64 |
audio_string | A public https link to the recording. Pass this or upload_id. maxLen: 2048 |
languagestring | The language spoken, or auto to detect it. Ruxsat etilgan qiymatlar: default: "auto" |
include_boolean | true adds the text in timed segments. default: false |
new_boolean | true makes a fresh take of an identical call from the last few minutes, and charges for it. Leave it out otherwise. |
Natija
| Maydon | Tavsif |
|---|---|
textstring | What was said. |
languagestring | The language, the detected one for auto. |
duration_number | How long the recording runs. |
segmentsobject[] | The text in timed pieces, when include_segments was true. |
segments[]number | |
segments[]number | |
segments[]string | |
costnumber | What the transcription cost, in credits. |
balancenumber | The organization's balance after the charge, in credits. |
replayedboolean | true when this repeats an identical call from the last few minutes, which charged nothing more. |
request_string | This call's request id, for support. |
clone_voice
Yuklangan namunadan ovoz kloni yaratadi.
- Ruxsat
voices:write- Narx
- Bepul
Assistent nimani oʻqiydi
Creates a voice clone from a short recording of one speaker (10 to 15 seconds) that the user has on their computer. Call create_upload with purpose voice_sample, run its curl command, then pass the upload_id; a link (audio_url) is not accepted. The speaker must have agreed to have their voice cloned, and speaker_consent: true confirms it: set it only when the user says the speaker agreed. Samples are wav, mp3, ogg, flac, up to 10 MB; ref_text is required: what the sample says, word for word, because the voice is paced from it. If the user cannot give it, transcribe the sample with speech_to_text and check the text with them. Use the new voice's id as voice_id in text_to_speech and text_to_dialogue. An identical call within 10 minutes answers with the voice it made instead of a second clone.Parametrlar
| Parametr | Tavsif |
|---|---|
namestringMajburiy | A name for the voice. maxLen: 120 |
languagestringMajburiy | The language the sample is spoken in. Ruxsat etilgan qiymatlar: |
upload_stringMajburiy | The upload_id from create_upload with purpose voice_sample, once the file is uploaded. maxLen: 64 |
speaker_booleanMajburiy | true confirms that the speaker agreed to have their voice cloned. Only true is accepted. Ruxsat etilgan qiymatlar: |
ref_stringMajburiy | What the sample says, word for word. The voice is paced from it, so it must match the recording. maxLen: 1000 |
tagsstring[] | Optional labels for the voice. |
categorystring | What the voice is for. characters when left out. Ruxsat etilgan qiymatlar: |
Natija
| Maydon | Tavsif |
|---|---|
voiceobject | The new voice clone. |
voice.string | Use it as voice_id. |
voice.string | |
voice.string | |
voice.string | Ruxsat etilgan qiymatlar: |
voice.string[] | |
voice.string | |
voice.string | |
replayedboolean | true when this is the voice an identical call made, and no second clone was made. |
request_string | This call's request id, for support. |
delete_voice
Ovoz klonlaringizdan birini oʻchiradi.
- Ruxsat
voices:write- Narx
- Bepul
Assistent nimani oʻqiydi
Deletes one of the organization's voice clones for good, by the id list_voices shows for it. Stock voices cannot be deleted. Confirm with the user first: the voice cannot be brought back, and anything that uses its id stops working. If it answers not_found, the voice is already gone or was never the organization's.Parametrlar
| Parametr | Tavsif |
|---|---|
voice_stringMajburiy | The id of the voice clone to delete. maxLen: 191 |
Natija
| Maydon | Tavsif |
|---|---|
deletedboolean | true once the voice clone is gone. |
voice_string | The id of the voice clone that was deleted. |
request_string | This call's request id, for support. |
Audio fayllar
Nutq Opus faylga havola sifatida qaytadi (assistent soʻrasa, MP3 yoki WAV). MCP Apps koʻrsatadigan mijozlar, masalan Claude, uni chatning oʻzida ham ijro etadi. Uni tinglash yoki yuklab olish uchun havolani brauzerda oching.
Havola 24 soatgacha ishlaydi va u kimda boʻlsa, oʻsha uni ocha oladi, shuning uchun uni faylning oʻzi kabi ehtiyot bilan ulashing. Claude va ChatGPT uni siz uchun ochmaydi.
Havolalarni ocha olmaydigan assistent, masalan sandboxdagisi, xuddi shu audioni MCP orqali natijada koʻrsatilgan resurs sifatida oʻqiy oladi. Oʻqish bepul va 40 MB gacha.
Kompyuterdagi fayllar
Kompyuterdagi fayldan yozuvni matnga aylantirish yoki ovozni klonlash uchun assistent create_upload ni chaqiradi, qaytgan curl buyrugʻini bajaradi, soʻng vositaga upload_id ni beradi. Windowsʼda u buyruqni curl.exe sifatida ishga tushiradi, chunki PowerShellʼda curl boshqa buyruq.
Yuklash havolasi 60 daqiqa ishlaydi va transkripsiya uchun 25 MB gacha, ovoz namunasi uchun 10 MB gacha fayl qabul qiladi. Yuklash uchun buyruq qatori kerak, shuning uchun u Claude yoki ChatGPTʼda emas, CLIʼlarda ishlaydi. Buyruqlarni sandboxda bajaradigan CLI, masalan Codex, yuklash uchun internetga chiqishga ruxsat berishi kerak.
Tashkilotda bir vaqtning oʻzida 3 tagacha yuklash davom etishi mumkin, bir soatda esa 30 tagacha yuklash havolasi olinadi.
Internetdagi yozuvlar
speech_to_text audio_url ni ham qabul qiladi: yozuvning ochiq https manzili. Claude va ChatGPTʼda audioni matnga shunday aylantirasiz. Havola faylning oʻziga olib borishi kerak: Google Drive yoki OneDrive ulashish sahifasi mos kelmaydi, Dropbox havolasiga esa dl=1 qoʻshing.
NeuronAI yozuvni oʻzi yuklab oladi. U koʻpi bilan 3 ta qayta yoʻnaltirishdan oʻtadi, shaxsiy va mahalliy manzillarga murojaat qilmaydi va transkripsiya hajmi limitida toʻxtaydi. Yuklab boʻlmasa, xato sababini aytadi, masalan taqiqlangan manzil yoki juda katta fayl.
Ovozni klonlash
clone_voice havolani emas, faqat yuklangan faylni hamda soʻzlovchi ovozi klonlanishiga rozi boʻlganini tasdiqlaydigan speaker_consent: true ni qabul qiladi. Claude va ChatGPTʼda ovozlarni boshqaruv panelida klonlang.
Narxlar va limitlar
Vositalar APIʼga yuborilgan xuddi shunday soʻrovlar bilan bir xil turadi va tashkilotingiz kreditlaridan toʻlanadi:
text_to_speech- Har bir belgi uchun 0,3 kredit, ovoz kloni bilan 0,5 kredit
text_to_dialogue- Har bir belgi uchun 0,3 kredit, ovoz kloni bilan 0,5 kredit
speech_to_text- Audioning har bir soniyasi uchun 1 kredit
Qolgan vositalar bepul.
10 daqiqa ichidagi aynan bir xil chaqiruv oxirgi natijani qaytaradi va pul yechmaydi, shuning uchun qayta urinish hech qachon ikki marta toʻlanmaydi. Boshqa variant olish uchun new_take: true ni yuboring, u qayta toʻlanadi.
Server har bir kalit yoki ulangan ilovadan daqiqasiga 120 tagacha soʻrov qabul qiladi. Bundan tashqari, har bir vosita oʻz mahsulotining APIʼdagi tezlik va bir vaqtdagi soʻrovlar limitlariga amal qiladi, rad javobi esa qancha kutish kerakligini aytadi.
text_to_speech audioni 40 soniyagacha kutadi. Uzunroq matnga u job_id bilan javob beradi va assistent tavsiya etilgan kutishdan soʻng u bilan get_speech ni chaqiradi. Muvaffaqiyatsiz tugagan vazifa uchun pul yechilmaydi.
Uzoq chaqiruvlar ish davomida jarayon haqida xabar berib turadi, shuning uchun ulanish uzilmaydi. Agar tool_timeout_sec oshirilmasa, Codex vositani 60 soniyadan soʻng toʻxtatadi: uning yorligʻi bu qiymatni 180 ga sozlaydi. Boshqa har qanday mijozga kamida 180 soniya bering.
Xavfsizlik
Ulangan ilova ulanishda tanlangan bitta tashkilot uchun ishlaydi va oʻsha tashkilot kreditlarini sarflaydi. Istalgan aʼzo uni «Dasturchilar», keyin «MCP» boʻlimida koʻrishi va darhol uzishi mumkin.
Har bir ulangan ilovaning API kalitlar sahifasida «Ulangan ilova» deb belgilangan oʻz kaliti bor. Unga oʻsha yerda oylik sarf limitini bering: assistent oʻqiydigan sahifa uni pullik vositalarni chaqirishga undashi mumkin.
Aʼzo tashkilotdan chiqarilsa, u ulagan ilovalar uziladi.
Skriptlar uchun faqat MCPʼga moʻljallangan, tts:write, voices:write va stt:write ruxsatlari bilan cheklangan alohida kalit yarating. Uni hech qachon repozitoriyga qoʻshmang: muhit oʻzgaruvchisida saqlang.
Ovozni faqat uning egasi rozi boʻlsa klonlang. clone_voice faqat yuklangan faylni qabul qiladi va rozilikni speaker_consent: true bilan tasdiqlashni soʻraydi.
Matnlar, transkripsiyalar va audio havolalar AI provayderingiz orqali, uning shartlari asosida oʻtadi. U bilan baham koʻrmaydigan narsangizni yubormang.
Muammolarni hal qilish
| Muammo |
|---|
NeuronAI sahifasi ochilmaydi yoki «Bu kirish havolasi ishlamaydi» deb koʻrsatadi Ilovadan ulanishni qaytadan boshlang. Bu takrorlansa, ilova hozircha NeuronAIʼni qoʻllamasligi mumkin: uni API kalit bilan ulang va bizga qaysi ilova ekanini xabar qiling. |
Claude qanday roʻyxatdan oʻtishni soʻraydi «Register automatically»ni tanlang. |
Ilova boshqa tashkilot kreditlarini sarflayapti «Dasturchilar», keyin «MCP» boʻlimini oching, ilovani uzing, soʻng uni qayta ulab, kerakli tashkilotni tanlang. |
ChatGPTʼda «Add custom MCP server» yoʻq yoki u faqat oʻqiy oladi Barcha vositalar brauzerdagi ChatGPT Business, Enterprise va Edu tariflarida ishlaydi, Businessʼda esa serverni administrator qoʻshadi. ChatGPT Pro faqat ovozlar roʻyxatini olishi va nutq vazifalarini tekshirishi mumkin. Plus, Go va Free tariflarida shaxsiy MCP serverlar yoʻq. |
Gemini CLI brauzerni ochmaydi Gemini CLIʼda |
Vosita roʻyxatda yoʻq yoki Kalit yoki ulanishda bu vosita uchun ruxsat yoʻq, assistent esa faqat chaqira oladigan vositalarni koʻradi. Kalitga xabarda koʻrsatilgan ruxsatni bering. |
Uzoq chaqiruvlar kutish vaqti tugab uziladi Mijozga Codex yorligʻidagi kabi kamida 180 soniyalik vosita kutish vaqtini bering. 10 daqiqa ichidagi aynan bir xil chaqiruv oxirgi natijani qayta pul yechmasdan qaytaradi. |
Mijoz kalitingiz oʻrniga Dock yoki Start menyusidan ochilgan ilova terminalda berilgan oʻzgaruvchilarni koʻrmaydi. Uni |
Claude Code uzun transkripsiyani faylga saqlaydi Claude Code 50 mingdan ortiq belgili vosita natijasini faylda saqlaydi va modelga uning faqat bir qismini koʻrsatadi. Undan faylni oʻqishni soʻrang va vaqt belgilari kerak boʻlmasa, |
Kalit yoki kirish rad etilsa
Server bu kodlar bilan vosita ishga tushishidan oldin javob beradi, ilova esa odatda kodni koʻrsatadi.
| Kod | Nima qilish kerak |
|---|---|
invalid_401 | Kalit nomaʼlum, ilova uzilgan yoki uning kirishi tugagan. Kalitni tekshiring yoki ilovani qayta ulang. |
api_401 | Kalit chaqirib olingan. Yangi kalit yarating yoki ilovani qayta ulang. |
api_401 | Kalit oʻchirib qoʻyilgan. «Dasturchilar», keyin «API kalitlar» boʻlimida uni qayta yoqing. |
api_401 | Kalitning muddati oʻtgan. «Dasturchilar», keyin «API kalitlar» boʻlimida muddatini uzaytiring yoki yangi kalit yarating. |
ip_403 | Soʻrov kalitning IP roʻyxatida boʻlmagan manzildan keldi. Manzilni roʻyxatga qoʻshing yoki roʻyxatdagi manzildan murojaat qiling. Claude va ChatGPT oʻz serverlaridan murojaat qiladi, shuning uchun ulangan ilova kalitining IP roʻyxati boʻsh boʻlishi kerak. |