Bawo ni mo ṣe lè gba bọ́tìnì API?

Ṣẹ̀dà fún kànẹ́lì TTS.ai ọ̀fẹ̀, ki o si lọ sí àká-ìṣàmúlò-ètò kànẹ́lì rẹ̀ ki o tẹ "Ṣẹ̀dà Bọ́tìnì API." Bọ́tìnì rẹ̀ á jẹ́ àwọn àmì-àṣírí àti àwọn àmì-àṣírí sk-tts- ki o si lè lò nígbà. Kànẹ́lì ọ̀fẹ̀ náà gba àwọn àmì-àṣírí 15,000 láti bẹrẹ.

Àwọn API náà ní ìṣàfarawé àwọn ìṣàmúlò-ètò OpenAI?

Ya, API wa nínú àwọn ìṣàmúlò-ètò ìtàn atí ìṣàfihàn tí a bá fẹ́ OpenAI. Tí o bá ní àwọn àyọkà tí a tì wa tí n lo TTS API OpenAI, o lè yipada sí TTS.ai láti fi àwọn ìṣàmúlò-ètò URL àtí bọ́tìnì API pamọ́ láti mú àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò

Àwọn ìsàlẹ̀-ilà ìṣàmúlò-ètò wo ní a fọwọ́sì?

REST API n ṣiṣẹ́ pẹlú àwọn ìtàn wò nípa tí a lè ṣé àwọn ìtàn HTTP. A ǹfi àwọn ààyè-iṣẹ́ ìṣàmúlò-ètò pamọ́ nínú Python, JavaScript (Node.js atí ìṣàfihàn), cURL, àtì diẹ́ sii. Àwọn ìtàn wò nípa àwọn àwọn láìbéètì HTTP (Go, Ruby, Java, C#, PHP, abbl.) lè ló API náà.

Kini àwọn ìdájọ́ àwọn ìṣàmúlò-ètò API?

Àwọn ìṣàmúlò-ètò ọ̀fẹ̀ ní àwọn ìṣàmúlò-ètò 3 lọ́wọ́lọ́wọ́. Àwọn ìṣàmúlò-ètò tí a pàyàn ní àwọn ààyè tí o gà jù lọ́wọ́lọ́wọ́ lọ́wọ́lọ́wọ́: Aṣàfilọ́lẹ̀ (60/ọ̀rọ̀ọ̀rọ̀), Aṣàfilọ́lẹ̀ (300/ọ̀rọ̀ọ̀rọ̀), Aṣàfilọ́lẹ̀ (ọ̀fẹ́). Àwọn àkọlé àwọn ààyè-ètò àwọn ìṣàmúlò-ètò ní àwọn ìṣàfilọ́lẹ̀ API ní gbogbo wọn.

Bawo ni API ṣe n ṣiṣẹ?

Àwọn àmì-àṣírí API lo àwọn àmì-àṣírí láti dáju àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn àmì-àṣírí. Àwọn àmì-àṣírí ọ̀fẹ̀ lo àwọn àmì-àṣírí 0, àwọn àmì-àṣírí ìpéwọ̀n lo àwọn àmì-àṣírí 2x, àti àwọn àmì-àṣírí ìpele lo àwọn àmì-àṣírí 4x. Àwọn àmì-àṣírí nínú àwọn àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò gbogbò nínú àwọn àwọn àwọn àmì-àṣírí tí a fi saǹ nínú àwọn àwọn àwọn àmì-àṣírí.

Àwọn ààyè-iṣẹ́ wo ní wa?

The API provides endpoints for text-to-speech (POST /v1/tts/), speech-to-text (POST /v1/transcribe/), voice cloning (POST /v1/voice-clone/), voice conversion (POST /v1/voice-convert/), speech translation (POST /v1/speech-translate/), audio enhancement (POST /v1/audio-enhance/), vocal removal, stem splitting, key and BPM analysis, and more.

Àwọn ìrísí-lẹ́tà àwòrán wo nínú àwọn API náà?

API náà náà gba àwòrán padà sí ìwọ̀n WAV nípa ìpéwọ̀n. O lè sọ ìwọ̀n àwọn ìṣàfihàn (mp3, wav, ogg, flac) láti lò àwọn àwọn ìṣàfihàn_ìpàrátì. MP3 ní a ṣè fọwọ́sì fún àwọn ìṣàmúlò-ètò wẹ́ẹ̀bù, WAV fún ìṣàfihàn àwòrán láti sàlẹ̀.

Is there a streaming API for real-time TTS?

Yes, our async API returns a job UUID that you can poll for results. For supported models like Kokoro, audio generation is fast enough for near-real-time applications. The polling endpoint returns the audio URL when processing is complete.

Bawo ni mo ṣe le ṣe ìdájọ́ àwọn àṣiṣe nínú API?

API náà náà gba àwọn àkóónú ìṣàmúlò-ètò HTTP ìṣàmúlò-ètò (400 fún àwọn ìtàn àìdá, 401 fún àwọn àṣìṣe ìṣàmúlò-ètò, 429 fún àwọn ìpàdé àwọn ìṣàmúlò-ètò, 500 fún àwọn àìdá àwọn sáà) láti ń jẹ́ àwọn àmì-ìwé àwọn àyọkà àyọkà JSON. Lórí ìṣàmúlò-ètò àti àwọn ààyè-iṣẹ́ àwọn àyọkà àyọkà nínú àwọn ìṣàfihàn fún ìṣàfihàn àwọn àyọkà náà.

Ń lè ló API fún àwọn ìṣàmúlò-ètò ọ̀fẹ́?

Òyà, API náà tí a kọ̀ fún ìlòdúrò. Àwòrán tí a ṣẹ̀dà láti inú API lè lò nínú àwọn nǹkan rẹ, àwọn ìṣàmúlò-ètò, àti àwọn iṣẹ́. Àwọn móòdù gbogbo náà lò àwọn láìsì àìfilọ́lẹ̀-ìṣàfilọ́lẹ̀, àti àwọn ẹ̀yàn àwọn ẹ̀yàn tí a ṣẹ̀dà.

Àwọn ààyè-iṣẹ́ àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn

Àwọn àwọn àwòrán àìdálẹ̀ àìdálẹ̀ ọ̀fẹ́ (Kokoro, Piper, VITS, MeloTTS) jẹ́ àwọn àwọn àwọn àwòrán àìdálẹ̀ tí a lò nípa àwọn àwọn àmì-ìwé àìdálẹ̀. Jẹ́ àwọn àwòrán àìdálẹ̀ ọ̀fẹ́ láti fi pamọ́ sí àwọn àwòrán àìdálẹ̀ àìdálẹ̀ àìdálẹ̀ fún ìlòòrò.

Bawo ni mo ṣe lè fi àwọn ìrànwọ́ àti àwọn ìṣàmúlò-ètò tí a nì láti inú API?

Lo GET /v1/voices láti fi àwọn ìrànwọ́ àwọn ìrànwọ́ àwọn ìrànwọ́ àwọn ìṣàmúlò-ètò ìṣàfihàn (móòdù, ìtàn, ìṣàfihàn). Lo GET /v1/models láti fi àwọn ìrànwọ́ àwọn ìrànwọ́ TTS àti àwọn ìpéwọ̀n àti àwọn ìròyìn àwọn ìṣàfihàn. Àwọn ìṣàfihàn mejeeji ń fi àwọn ìṣàfihàn JSON sí.

TTS.ai API Documentation - Àkọlé sí Àkọlé REST API

Àwọn ìṣàmúlò-ètò

TTS.ai API náà náà gba ìwọlé ìṣàmúlò-ètò fún àwọn àbùdá àwọn ààyè-iṣẹ́ gbogbó: àkọlé-si-ìbàlẹ̀, àkọlé-si-ìbàlẹ̀, ìṣàfarawe-ìbàlẹ̀, ìṣàfihàn àwọn àwòrán, àti àwọn mìíràn. API náà náà ló àwọn ìṣàmúlò-ètò REST ìṣàfarawe-ètò láti mú àwọn ẹ̀yàn ìṣàfihàn/ìjánú ìṣàfihàn JSON.

Bọ́tìnì API

Gba àwọn bọ́tìnì API rẹ̀ láti Àwọn Ààtòjú Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn. Wa ni Pro ati Enterprise plans.

URL Ìdálẹ̀

https://api.tts.ai/v1/

Àwọn Àmì-ìwé

Àwọn Ìṣàmúlò-ètò Authorization àwọn àmì-ìwé

Àwọn Ìṣàmúlò-ètò

Àwọn ìpele àìfẹ́fẹ́ — kò ní bọ́tìnì kan tí a fẹ́. Àwọn àkọlé àìdálẹ̀ /v1/tts/ iṣẹ́ laisi àwọn ẹ̀yàn, lọ́wọ́lọ́wọ́ si 5,000 àwọn àmì-àṣírí/ọ̀jọ̀ kan nípa IP kan, nípa lòjútó àwọn módè́lì ọ̀fẹ́ wa (piper, vits, melotts, kokoro). Ṣabẹwo fun kaadi iroyin ọfẹ lati gba awọn aami 15,000 ti o dara julọ ati wọle si awọn awoṣe premium.

Fun àwọn ìṣàmúlò-ètò àti àwọn ìpéjúwé ìṣàmúlò-ètò tí o gà jú, ṣàfihàn láti ló tókè Béèrì nínú Authorization àwọn àmì-ìwé.

Àwọn Àmì-ìwé HTTP

Authorization: Bearer sk-tts-your-api-key-here

Fi àwọn bọ́tìnì API rẹ pamọ́. Kò pẹ̀lú àwọn ìṣàmúlò-ètò ààyè-iṣẹ́, àwọn ìpamọ́ àwọn alábòójútó alábòójútó, tàbí àwọn ìṣàmúlò-ètò. Àwọn bọ́tìnì ìṣàfihàn láti inú àtòjọ-ẹ̀yàn rẹ̀.

Àwọn SDK

SDKs Oṣójọ́lẹ̀ ṣé ìmọ̀ràn láti fi TTS.ai pamọ́ sínú ìṣàmúlò-ètò rẹ̀. Wọ́n ní afẹ́fẹ́ àwọn ìṣàmúlò-ètò náà, àti àwọn náà ní a lè gba nípa GitHub.

Python

pip install ttsai

from tts_ai import TTSClient

client = TTSClient(api_key="sk-tts-...")
audio = client.generate(
    text="Hello world!",
    model="kokoro"
)
client.save(audio, "output.wav")

GitHub

JavaScript / Node.js

npm install @ttsainpm/ttsai

const { TTSClient } = require('@ttsainpm/ttsai');

const client = new TTSClient({
  apiKey: 'sk-tts-...'
});
const audio = await client.generate({
  input: 'Hello world!',
  model: 'kokoro'
});
await client.saveToFile(audio, 'output.wav');

GitHub

URL Ìdálẹ̀

URL Ìdálẹ̀: https://api.tts.ai/v1/

Àwọn ààyè-iṣẹ́ ìparí gbogbó ní pàtó nípa URL̀ ìtọ́nà yìí. Fun ààyè-iṣẹ́ ìparí TTS ni:

POST https://api.tts.ai/v1/tts/

Àwọn Ìdálẹ̀ Ìjánu-ìṣàmúlò-ètò

Àwọn ìdájọ́ àwọn ìṣàmúlò-ètò API nípa àwọn ìṣàmúlò-ètò:

Àwọn ààyè-iṣẹ́	Àwọn Ìtàn/minútùù	Àwọn ìṣàfarawé	Ìgbà pípẹ́ àkọlé pípẹ́ jú
Àìfẹ́	10	2	Àwọn àmì-ìwé 500
Àwọn Ìṣàmúlò-ètò	30	3	Àwọn àmì-ìwé 1,000,000
Àwọn Àwọn Àwọn	60	5	Àwọn àmì-ìwé 1,000,000
Àwọn Ìṣàfilọ́lẹ̀	300	20	Àwọn àmì-ìwé 50,000

Àwọn àmì-ìwé-ìwé ìdáràn nínú àwọn ìsàlẹ̀-ilà gbogbo: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset.

Àwọn Ìṣàmúlò-ètò

Àwọn Àṣẹ	Àwọn Irinṣẹ́	Àwọn Ìgúnrégé
TTS (Móòdù Fẹ́ẹ̀: Piper, VITS, MeloTTS)	Àwọn àyọkà 1,000	fún àwọn àmì-àṣírí 1,000
TTS (Móòdù ìpèwọ̀n: Kokoro, CosyVoice 2, abbl.)	Àwọn àyọkà 2,000	fún àwọn àmì-àṣírí 1,000
TTS (Móòdù Premium: Tortoise, Chatterbox, abbl.)	Àwọn ìṣàmúlò-ètò	fún àwọn àmì-àṣírí 1,000
Àwọn Àmì-ìwé	Àwọn àyọkà 2,000	Àwọn àwọn àwòrán
Àwọn Àmì-ìwé	Àwọn ìṣàmúlò-ètò	fún àwọn àmì-àṣírí 1,000
Àtòjọ-ẹ̀yàn Àwọn Àmì-ìwé	Àwọn àyọkà 3,000	Àwọn àwọn àwòrán
Àwọn ìṣàfarawé àwòrán	Àwọn àyọkà 2,000	Àwọn àwọn àwòrán
Ìjádè àwọn àmì-ìwé / Ìjádé àwọn àmì-ìwé	Àwọn àyọkà 3,000-4,000	Àwọn àwọn àwòrán
Àwọn ìṣàfarawé kọ̀ǹpútà	Àwọn àyọkà 5,000	Àwọn àwọn àwòrán
Àkọlé àwòrán	Àwọn àyọkà 3,000	Àwọn ìṣàfarawé àwọn ààyè-iṣẹ́
Alábòójútó Bọ́tìnì BPM	Àìfẹ́	--
Àwọn Ìjánu-ìṣàmúlò-ètò	Àìfẹ́	--

Àkọlé sí Àkọ́kọ́

POST /v1/tts/

Ṣàfikún àyọkà náà sí àwòrán àkọlé. Ṣàfikún fáìlì àwòrán nínú ìrísí-lẹ́tà tí a beere.

Àwọn ìṣàmúlò-ètò

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
model	string	No	ID Móòdù (gẹ́gẹ́ bí `kokoro`, `chatterbox`, `piper`). Tí a bá fi pà, a á yan móòdù tí ó bá jẹ́ ìrànwọ́ àwọn `àkànṣe` tí a bì - `kokoro` fún en/ja/zh/ko/fr/de/it/pt/es/hi/ru, `piper` fún àwọn àkànṣe mìíràn tí a bá jẹ́ ìrànwọ́ (ar/pl/nl/cs/da/fi/el/hu/tr/uk/vi/etc.).
text	string	Yà	Àkọlé tí a fẹ́ láti yipada sí ìṣàfarawé (àwọn àmì-ìwé 100,000 lórí ìtàn)
voice	string	Yà	Àtòjọ Àwọn Àwòrán (lo `/v1/voices/` láti ṣàfihàn àwọn àwòrán tí a ní)
format	string	No	Àwọn ìṣàmúlò-ètò àwọn ààtò: `mp3` (ò̀tọ́), `wav`, `flac`, `ogg`
speed	float	No	Àwọn ìṣàfarawé ìpele ìṣàfihàn. Àwọn ìpéwọ̀n: `1.0`. Àwọn ìpele: `0.5` sí `2.0`
language	string	No	Àtòjọ-ètò ìtàn (gẹ́gẹ́ bíi, `en`, `es`). Àtòjọ-ètò ìṣàfilọ́lẹ̀ láti inú ìṣàfilọ́lẹ̀.
instructions	string	No	Àwọn àwọn àgbékalẹ̀/àfilọ́lẹ̀ (àtí àwọn àmì-ìwé ≤500). e.g. `\`
pronunciations	object \| array	No	Àwọn ìṣàfarawé àwọn ìṣàfihàn-nípa-ìgbègbè. Àwọn `{\`
stream	boolean	No	Fún àwọn àgbéwọlé ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu-ìjánu

Àwọn ìṣàmúlò-ètò

cURL

curl -X POST https://api.tts.ai/v1/tts/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kokoro",
    "text": "Hello from TTS.ai! This is a test.",
    "voice": "af_bella",
    "format": "mp3"
  }' \
  --output output.mp3

Àwọn àmì-ìwé SSML

Wrap numbers, dates, currency, phone numbers, and acronyms in <say-as interpret-as="..."> tags so the model speaks them naturally instead of guessing.

Àwọn àkọlé	Àwọn Ìjánu-ìwé	Tí a Fi Wí
`cardinal`	`1234`	one thousand two hundred thirty-four
`ordinal`	`21`	twenty-first
`date`	`1999-12-31`	December thirty-first, nineteen ninety-nine
`time`	`14:30`	two thirty PM
`telephone`	`+1-555-867-5309`	plus one five five five eight six seven…
`currency`	`$1,234.56`	one thousand two hundred thirty-four dollars and fifty-six cents
`spell-out`	`NASA`	N A S A

Date format defaults to mdy for English and dmy elsewhere; override with format="ymd|mdy|dmy". Currency auto-detects $/€/£/¥; pass currency="USD|EUR|GBP|JPY|CAD|AUD|MXN|INR|CNY" to set it explicitly. Tags work in any language; English is fully supported, other languages use num2words where available.

Àwọn Ààyè-iṣẹ́

{
  "model": "kokoro",
  "voice": "af_bella",
  "text": "Your appointment is on <say-as interpret-as=\"date\">2026-04-26</say-as> at <say-as interpret-as=\"time\">14:30</say-as>. Please call <say-as interpret-as=\"telephone\">+1-555-867-5309</say-as> if you need to reschedule."
}

Àwọn ìsàlẹ̀-ilà

The TTS endpoint queues your request and returns a JSON response with a job UUID. You then poll for the result.

Step 1: Submit request

Response (JSON)

{
  "uuid": "77b71db532874ce98e84a69a2d740d4c",
  "job_id": "f21316bb-aefa-480d-8523-701d1e3184ce",
  "status": "queued",
  "credits_used": 11,
  "credits_remaining": 15000
}

Step 2: Poll for result

GET /v1/speech/results/?uuid=<job_uuid>

Poll this endpoint every 1-2 seconds until status is completed or failed.

Polling response (completed)

{
  "status": "completed",
  "result_url": "https://api.tts.ai/static/downloads/77b71db5.../output.mp3"
}

Polling response (still processing)

{
  "status": "processing"
}

Step 3: Download audio

Fetch the result_url from the completed response to download the audio file.

Full example

Python

import requests, time

API_KEY = "sk-tts-your-key"
BASE = "https://api.tts.ai"

# 1. Submit TTS request
resp = requests.post(f"{BASE}/v1/tts/", json={
    "model": "kokoro",
    "text": "Hello from TTS.ai!",
    "voice": "af_bella"
}, headers={"Authorization": f"Bearer {API_KEY}"})
data = resp.json()
uuid = data["uuid"]

# 2. Poll for result
while True:
    result = requests.get(f"{BASE}/v1/speech/results/",
        params={"uuid": uuid}).json()
    if result["status"] == "completed":
        # 3. Download audio
        audio = requests.get(result["result_url"])
        with open("output.mp3", "wb") as f:
            f.write(audio.content)
        break
    elif result["status"] == "failed":
        raise Exception(result.get("error", "Generation failed"))
    time.sleep(1.5)

Streaming alternative: For supported models (Kokoro, MeloTTS), use POST /v1/tts/stream/ for real-time Server-Sent Events (SSE) streaming — no polling needed.

Àwọn Àmì-ìwé

POST /v1/stt/

Ṣàfihàn àwòrán láti inú àkọsílẹ̀. Ṣàfihàn àwọn ètò 99 láti inú ìṣàfilọ́lẹ̀ àtòjọ-ètò.

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
file	file	Yà	Fáìlì àwòrán (MP3, WAV, FLAC, OGG, M4A, MP4, WebM). Max 100MB.
model	string	No	Àwọn àwọn àwòrán STT: `whisper` (pípálẹ̀), `faster-whisper`, `sensevoice`
language	string	No	Àtòjọ-ẹ̀yàn. `àtòjọ-ẹ̀yàn` fún ìṣàfihàn-àtòjọ-ẹ̀yàn (píríǹtì).
timestamps	boolean	No	Ṣàfikún àwọn àkóónú àkóónú. Àtòjọ-ẹ̀yàn: `fáìlì`
diarize	boolean	No	Mú ìṣàfilọ́lẹ̀ àwọn àkọlé àwòrán ṣiṣẹ́. Àtòjọ-ẹ̀yàn: `fáìlì`

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "text": "Hello, this is a transcription test.",
  "language": "en",
  "duration": 3.5,
  "segments": [
    {
      "start": 0.0,
      "end": 1.8,
      "text": "Hello, this is",
      "speaker": "SPEAKER_00"
    },
    {
      "start": 1.8,
      "end": 3.5,
      "text": "a transcription test.",
      "speaker": "SPEAKER_00"
    }
  ]
}

Àwọn Àmì-ìwé

POST /v1/tts/clone/

Ṣẹ̀dà àkọlé nínú àwòrán. Lọ́ọ̀kan àwòrán àti àyọkà ìṣàfilọ́lẹ̀.

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
reference_audio	file	Yà	Àwọn àwòrán àwòrán ìṣàfihàn (10-30 àwọn ìsàlẹ̀-ilà). Max 20MB.
text	string	Yà	Àkọlé láti sọ nínú ìrànwọ́ ìṣàfarawé.
model	string	No	Àwọn àwọn àwòrán: `chatterbox` (píríǹtì), `cosyvoice2`, `gpt-sovits`
format	string	No	Àwọn ìṣàmúlò-ètò àwọn ààtò: `mp3` (pípálẹ̀), `wav`, `flac`
language	string	No	Àtòjọ-ètò ìsàlẹ̀-ilà. Ò ní ìyànfàn láti inú àwọn móòdù tí a yàn.

Àwọn ìsàlẹ̀-ilà

Fi fáìlì ìsàlẹ̀-ilà àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò àwọn ìṣàmúlò-ètò TTS padà.

Àtòjọ-ẹ̀yàn Àwọn Àmì-ìwé

POST /v1/voice-convert/

Ṣàfikún àwòrán láti jẹ́ àwòrán ìṣàmúlò-ètò mìíràn. Ṣàfikún àwòrán ìṣàmúlò-ètò náà láti yan àwòrán ìṣàmúlò-ètò.

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
file	file	Yà	Fáìlì ìrísí-lẹ́tà (MP3, WAV, FLAC). Max 50MB.
target_voice	string	Yà	Àtòjọ-ẹ̀yàn àwòrán tí a fẹ́ láti yipada sí (lo `/v1/voices/` láti ṣàfihàn àwòrán tí a nì)
model	string	No	Móòdù ìyipadà àwòrán: `openvoice` (píríǹtì), `knn-vc`
format	string	No	Àwọn ìṣàmúlò-ètò àtòjọ-ẹ̀yàn: `wav` (píríǹtì), `mp3`, `flac`

Àwọn ìṣàmúlò-ètò

cURL

curl -X POST https://api.tts.ai/v1/voice-convert/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -F "file=@source_audio.mp3" \
  -F "target_voice=af_bella" \
  -F "model=openvoice" \
  -o converted.wav

Àwọn ìsàlẹ̀-ilà

Fi fáìlì àwòrán tí a yipadà padà sí bí àwọn ààtòjọ-ẹ̀yàn àìṣàfilọ́lẹ̀.

Àwọn ìṣàfarawé kọ̀ǹpútà

POST /v1/speech-translate/

Ṣàfihàn àwòrán tí a sọ láti inú ede kan sí mìíràn. Ṣàfihàn àwọn àkọlé-si-àkọlé, àwọn ìtumọ̀, àwọn àkọlé-si-àkọlé nínú awájú kan.

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
file	file	Yà	Fáìlì ìṣàmúlò-ètò ìsàlẹ̀-ètò nínú ìrísí-lẹ́tà ìṣàfarawé. Max 100MB.
target_language	string	Yà	Àtòjọ-ètò ìsàlẹ̀-ilà (gẹ́gẹ́ bíi `es`, `fr`, `de`, `ja`)
voice	string	No	Àwọn àwọn àyọkà ìṣàfihàn tí a tì tumọ̀. A yan nípa ìṣàfihàn látì jẹ́ pé a tì yọ̀.
preserve_voice	boolean	No	Àwọn ààyè-iṣẹ́ àwọn ìṣàfarawé àwọn àkọlé

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "original_text": "Hello, how are you?",
  "translated_text": "Hola, como estas?",
  "source_language": "en",
  "target_language": "es",
  "audio_url": "https://api.tts.ai/v1/results/translate_abc123.mp3",
  "credits_used": 5
}

Àwọn Àkọlé

POST /v1/speech-to-speech/

Ṣàfikún àwọn ìṣàmúlò-ètò ìṣàfihàn, àwọn ìrànwọ́, tàbí ìgbàdálẹ̀ nígbà tí o bá tọju àwọn ìṣàfihàn. Lòòròlò fún ìṣàfihàn àwọn ìṣàfihàn, àwọn ìṣàfihàn, àwọn ìṣàfihàn.

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
file	file	Yà	Fáìlì àwòrán ìṣàfihàn. Max 50MB.
voice	string	Yà	Àwọn àwọn àmì-ìwé àwọn àmì-ìwé àwọn àwọn àmì-ìwé
model	string	No	Àwọn ìṣàmúlò-ètò: `openvoice` (píríǹtì), `chatterbox`
emotion	string	No	Àkọ́lé àwòrán: `ọ̀fẹ́`, `ọ̀fẹ́`, `ọ̀pọ̀lú`, `ọ̀pọ̀lú`, `ọ̀pọ̀lú`
speed	float	No	Àwọn ìṣàmúlò-ètò ìṣàfarawé ìrànwọ́. Àwọn ìpéwọ̀n: `1.0`. Àwọn ìjánu-ìsún: `0.5` sí `2.0`

Àwọn ìsàlẹ̀-ilà

Fi fáìlì àwòrán tí a tì yipadà padà sí bí àwọn ààtòjọ-ìdákọ àwọn ìṣàfarawé.

Àwọn Àtòjọ-ẹ̀yàn Àkọsílẹ̀

Àwọn ààyè-iṣẹ́ ìparí ìṣàfarawé àwòrán fún ìṣàfarawé, ìjánu-ìṣàmúlò-ètò, ìjánu-ìṣàfilọ́lẹ̀, àti àwọn mìíràn mìíràn.

POST /v1/audio/enhance/

Ṣàfihàn àwọn ìṣàmúlò-ètò àwòrán: denoise, ìṣàfihàn ìwọ̀n, àwọn ìṣàfihàn nla.

file file	Fáìlì àwòrán tí a fẹ́ mú
denoise boolean	Ṣàfikún àwọn ìṣàmúlò-ètò tí a kò fẹ́ (òrò: òótọ́)
enhance_clarity boolean	Ṣẹ̀dà ìròyìn àkọlé ( ìpéwọ̀n: òótọ́)
super_resolution boolean	Ìdáràn àwọn ìṣàmúlò-ètò ìṣàfarawé àwọn ìṣàmúlò-ètò
strength integer	1-3 (ìwọ̀n, ìsàlẹ̀-ilà, ìpéwọ̀n). Àtòjọ-ẹ̀yàn: 2

POST /v1/audio/separate/

Ṣàfarawe àwọn àwòrán láti inú àwọn àkọlé (àwọ̀n àwòrán) tàbí fi àwọn àwọn àgbèwọlé pamọ́.

file file	Fáìlì àwòrán láti ṣí
model string	`demucs` (Àwọn ìpéwọ̀n) tabi `spleeter`
stems integer	Àwọn àwọn ìṣàmúlò-ètò: 2, 4, 5, tàbí 6 (òòrò: 2)
format string	Àwọn ìṣàmúlò-ètò ìjánu-ìṣàfilọ́lẹ̀: `wav`, `mp3`, `flac`

POST /v1/audio/dereverb/

Ṣàfikún àgbègbè àti àgbègbè láti inú àwọn àkọsílẹ̀ àwòrán.

file file	Fáìlì àwòrán láti ṣe ìṣàfarawé
type string	`echo` or `reverb` (default: both)
intensity integer	1-5 (default: 3)

POST /v1/audio/analyze/ Àìfihàn

Ṣàfihàn àwòrán láti ṣàfihàn bọ́tìnì, BPM, àti àwọn ìṣàmúlò-ètò àwọn ìṣàfihàn àkókò.

file file

Fáìlì ìsàlẹ̀-ilà láti ṣàfihàn

Àwọn ìsàlẹ̀-ilà

{
  "key": "C",
  "scale": "Major",
  "bpm": 120.0,
  "time_signature": "4/4",
  "camelot": "8B",
  "compatible_keys": ["C Major", "G Major", "F Major", "A Minor"]
}

POST /v1/audio/convert/ Àìfihàn

Ṣàfikún àwòrán laarin àwọn ìrísí-lẹ́tà.

file file	Fáìlì àwòrán láti yipada
format string	Àwọn ìgúnrégé àwọn àkọ́lé: `mp3`, `wav`, `flac`, `ogg`, `m4a`, `aac`
bitrate integer	Bítàrátì ìjánu-ìjánu nínú kbps: 64, 128, 192, 256, 320
sample_rate integer	Àwọn ìṣàmúlò-ètò:
channels string	`mono` tabi `stereo`

Àkọlé àwòrán

POST /v1/voice-chat/

Fi àwòrán tàbí àkọlé pamọ́ ki o si gba ìjánu-íjánu AI nípa ìṣàfarawe-ìrọ̀.

Àwọn ìṣàmúlò-ètò (multipart/form-data tabi JSON)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Tí a fẹ́	Àkóónú
audio	file	No*	Ààyè-iṣẹ́ àwòrán (yàni `àwòrán` tàbí `àyọkà` tí a fẹ́)
text	string	No*	Àwọn ìṣàmúlò-ètò àyọkà (ọ̀kan ninu `àwòrán` tàbí `àwòrán` tí a fẹ́)
voice	string	No	Àwòrán fún àgbékalẹ̀ AI. Àtòjọ-ẹ̀yàn: `af_bella`
tts_model	string	No	Àwọn ìṣàmúlò-ètò TTS fún àgbékalẹ̀. Àtòjọ-ẹ̀yàn: `kokoro`
system_prompt	string	No	Àwọn àgbèwọlé ìṣàmúlò-ètò fún AI
conversation_id	string	No	Lọ́wọ́lọ́wọ́ àkọlé tí wa

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "conversation_id": "conv_abc123",
  "user_text": "What is the capital of France?",
  "ai_text": "The capital of France is Paris.",
  "audio_url": "https://api.tts.ai/v1/audio/tmp/resp_xyz.mp3",
  "credits_used": 3
}

Àwọn àwọn àwọn àwọn àwọn

POST /v1/tts/batch/

Fi àwọn àkọlé àwọn ìṣàmúlò-ètò láti fi pamọ́ fún ìṣàfihàn TTS. Lọ́wọ́lọ́wọ́ gba àgbègbè wẹ́ẹ̀bùhookù láti inú àwọn iṣẹ́ láti pari.

Àwọn Àtòjọ-ẹ̀yàn

Àwọn Àtòjọ-ẹ̀yàn	Àwọn Ìṣàmúlò-ètò	Àwọn Àkọlé
texts	array	Array of objects: `{text, model, voice}`. Max 50 items.
webhook_url	string	Optional URL to POST results when batch completes.

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "batch_id": "abc123",
  "total": 3,
  "completed": 0,
  "status": "processing"
}

Àwọn ìṣàmúlò-ètò ìṣàfihàn àti GET /v1/tts/batch/result/?batch_id=abc123

Ìṣàfilọ́lẹ̀ Àwọn Àmì-ìwé

POST /v1/voice-embed/

Ṣàfikún ìṣàfilọ́lẹ̀ ìgbọ́ọ̀kan láti inú ìṣàfilọ́lẹ̀ ìgbọ́ọ̀kan. Lò àwọn àwọn ìṣàfilọ́lẹ̀_id tí a fi pamọ́ nínú àwọn ìtàn ìṣàfilọ́lẹ̀ ìgbọ́ọ̀kan láti mú ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ láti inú ìṣàfilọ́lẹ̀.

Àwọn Àtòjọ-ẹ̀yàn

Àwọn Àtòjọ-ẹ̀yàn	Àwọn Ìṣàmúlò-ètò	Àwọn Àkọlé
file	file	Reference audio file (WAV, MP3, FLAC).
model	string	Cloning model (default: chatterbox). Supported: chatterbox, cosyvoice2, openvoice, gpt-sovits, spark, indextts2, qwen3-tts.

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "embed_id": "emb_abc123",
  "model": "chatterbox",
  "duration_ms": 450
}

Àwọn Àwọn Ààyè-iṣẹ́

GET /v1/health/

Ṣayẹwo ìṣàmúlò-ètò àwọn ààtò GPU, àwọn àwọn ìṣàmúlò-ètò àti ìwọ̀n ìṣàmúlò-ètò. Kò ní ìṣàfihàn ìṣàfihàn. A fi àwọn ìṣàfihàn pamọ́ fún àwọn ìṣísẹ̀ 30.

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "status": "online",
  "latency_ms": 45,
  "queue_size": 3,
  "models_loaded": ["kokoro", "chatterbox", "cosyvoice2"]
}

Àtòjọ àwọn ìṣàmúlò-ètò

GET /v1/models/

Ṣàfihàn àtòjọ àwọn ìṣàmúlò-ètò tó lè wa nínú àwọn ìṣàmúlò-ètò wọn.

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "models": [
    {
      "id": "kokoro",
      "name": "Kokoro",
      "type": "tts",
      "tier": "standard",
      "languages": ["en", "ja", "ko", "zh", "fr"],
      "supports_cloning": false,
      "supports_streaming": true,
      "credits_per_1k_chars": 2
    },
    {
      "id": "chatterbox",
      "name": "Chatterbox",
      "type": "tts",
      "tier": "premium",
      "languages": ["en"],
      "supports_cloning": true,
      "supports_streaming": true,
      "credits_per_1k_chars": 4
    }
  ]
}

Àwọn Àmì-ìwé Àtòjọ

GET /v1/voices/

Ṣàfihàn àtòjọ àwọn àwòrán tó lè wa ní pàtó, àti àwọn ìṣàmúlò-ètò ìṣàfihàn láti inú àwòrán tàbí àwòrán.

Àwọn Àlàyé Àwọn Àwọn Ààtò

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Àkóónú
model	string	Píríǹtì láti inú ID ìṣàmúlò-ètò (gẹ́gẹ́ bíi `kokoro`)
language	string	Fi àwọn àmì-ìwé ìsàlẹ̀-ilà pamọ́ (gẹ́gẹ́ bíi `en`)
gender	string	Aṣàfilọ́lẹ̀ láti inú ìwọ̀n: `ọmọkunrin`, `ọmọbinrin`, `ọ̀kan-ọ̀kan`

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfihàn JSON

{
  "voices": [
    {
      "id": "af_bella",
      "name": "Bella",
      "model": "kokoro",
      "language": "en",
      "gender": "female",
      "preview_url": "https://api.tts.ai/v1/voices/preview/af_bella.mp3"
    }
  ],
  "total": 142
}

Àwọn àkọlé (SRT / VTT) new

GET /v1/speech/subtitles/?uuid=<job_uuid>&format=srt|vtt&download=1

Generate synchronised subtitles for any completed TTS job. Runs Whisper alignment over the audio and returns SRT or WebVTT. Result is cached on disk so a second call for the same uuid is a disk read.

Àwọn Àlàyé Àwọn Àwọn Ààtò

Àwọn ìkúndùǹ	Tí a fẹ́	Àkóónú
uuid	Yà	UUID iṣẹ́ tí /v1/tts/ tàbí /v1/voice-clone/ fi pamọ́.
format	No	`srt` (píríǹtì) tàbí `vtt`.
download	No	`1` lati fi `Ìṣàfihàn-Ìdákọ́ọ̀kan: àtòjọ-ẹ̀yàn` ranṣẹ ki awáròyìn náà fipamọ́ láti inú àwọn ìṣàfihàn.
language	No	Àwọn ìṣàmúlò-ètò fún àwọn móòdù ìṣàfarawé (tí a bá gbọ́ nípa ìṣàfihàn).

cURL

curl "https://api.tts.ai/v1/speech/subtitles/?uuid=$UUID&format=srt&download=1" -o subtitles.srt

Àwọn Àwọn Àkọlé new

GET POST DELETE /api/v1/pronunciations/

Fi àwọn àwọn àgbéwọlé tí a fi pamọ́ pamọ́ sínú àwọn àgbéwọlé TTS. Àwọn àgbéwọlé tí a fi pamọ́ láti lo nípa àwọn ìṣàfilọ́lẹ̀ TTS gbogbò tí o ṣe. Ìgbà ìṣàfilọ́lẹ̀ 200 fun àwọn àgbéwọlé kan.

Àwọn ìṣàmúlò-ètò (POST)

Àwọn ìkúndùǹ	Àwọn Ìṣàmúlò-ètò	Àkóónú
word	string	Word to override (e.g. `GIF`, `Anthropic`). Word-boundary matched.
replacement	string	Bii o ṣe le sọ ọ̀rọ̀ rẹ̀ fun àwọn móòdù (gẹ́gẹ́ bi `jiff`, `ann THROP ick`).
language	string	Àwọn ìkúndùǹ ISO tí a fẹ́. Tí kò bá jẹ́ = lò fún gbogbo àwọn ìtàn.
case_sensitive	boolean	Default `false`. Match case exactly when `true`.

cURL

# Save an entry
curl -X POST https://tts.ai/api/v1/pronunciations/ \
  -H "Authorization: Bearer sk-tts-..." \
  -H "Content-Type: application/json" \
  -d '{"word": "GIF", "replacement": "jiff"}'

# List your entries
curl https://tts.ai/api/v1/pronunciations/ -H "Authorization: Bearer sk-tts-..."

# Delete entry by id
curl -X DELETE "https://tts.ai/api/v1/pronunciations/?id=42" -H "Authorization: Bearer sk-tts-..."

You can also pass per-request overrides without saving them — include pronunciations on any /v1/tts/ call as either an object or an array (see the TTS endpoint params).

Àwọn Àkọlé new

Drop a single <script> tag on any article page and visitors get a fixed reader bar that narrates the page on click. Auto-detects the article body, supports custom voice / model / position / accent color.

HTML

<script src="https://tts.ai/narrator.js"
    data-pk="pk-tts-your-publishable-key"
    data-voice="af_bella"
    data-model="kokoro"
    data-extract="auto"
    data-position="bottom"
    data-color="#e60000"
    data-locale="en"></script>

Àwọn Àtòjọ-ẹ̀yàn

Àwọn ìkúndùǹ	Àkóónú
`data-pk`	Bọ́tìnì àìfihàn (pk-tts-…). Àwọn ìdájọ́ dómìǹì tí a fi pamọ́ láti inú ààyè-iṣẹ́ `àwọn_dómìǹì_tí a_fàyè gba` bọ́tìnì náà.
`data-voice`	Àwọn àmì-ìwé àwòrán. `af_bella` ìpèwọ̀n.
`data-model`	TTS model ID. Default `kokoro`.
`data-extract`	`auto` (default) — tries article/main/.post-content/.entry-content selectors, falls back to densest paragraph cluster. Or pass any CSS selector to target a specific element.
`data-position`	`bottom` (píríǹtì) tàbí `top`.
`data-color`	Àwọ́ àwọn àyọkà ìṣàfarawé (ọ̀kan àwòrán CSS). Àwọn ìpéwọ̀n `#e60000`.
`data-min-chars` / `data-max-chars`	Lọ́nà àkànṣe náà tí àkọlé bá jú àwọn àmì-àṣírí ìsàlẹ̀-ilà tó kéré jú (òkù ìpéwọ̀n 200). Fẹ́ àwọn àmì-àṣírí láti inú àwọn àmì-àṣírí ìparí (òkù ìpéwọ̀n 50,000).

Àkọlé àwòrán

Àwọn Àwọn Àtòjọ-ẹ̀yàn

Inline button-style embed. Renders next to its <script> tag and plays a button-triggered short snippet. Different shape from the Article Narrator above (which auto-injects a page-spanning bar and narrates the whole article).

HTML

<script src="https://tts.ai/widget.js"
    data-voice="af_bella"
    data-model="kokoro"
    data-style="full"
    data-theme="light"></script>

Àwọn Àwòrán Tí A Fi Pamọ́ (Àwọn Kọlọ̀nì Tí A Fẹ̀)

Fi àwòrán àwòrán ìṣàfihàn pamọ́ nígbà kan, gba àwòrán_àwòrán tí a tílẹ̀, láti rí àwòrán àwòrán náà nínú àwọn ìtàn TTS láti fi àwòrán àwòrán pamọ́ padà nígbà gbogbo. Ó jẹ́ ìṣàfihàn fún àwọn ìṣàfihàn ìpele-òkè.

Àwọn ìṣàmúlò-ètò Ìpamọ́ jẹ́ ọ̀fẹ́ (kò sí ìyàn ọjọ́, kò sí ìgbà ìpa. Ìfihàn: àwọn àmì-àṣírí 500 nígbà kan fún ohun kan. Ìlò-ìlò: àwọn àmì-àṣírí +50 tí a fi kun àwọn ìṣàfilọ́lẹ̀ TTS fún àwọn àwọn ìṣàfilọ́lẹ̀ tí a fi pamọ́, nínú àwọn àwọn àwọn àwọn àwọn ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀. Fi àwọn àwòrán pamọ́ tí o kò fẹ́ nígbà yìí láti fi wọn pamọ́; pàtó wọn nígbà tí o bá fẹ́. Gbogbo àwọn ní àwọn awáròyìn API ọ̀fẹ́.

Fi àwòrán pamọ́

POST https://tts.ai/api/v1/user-voices/ Àwọn ìṣàfihàn

Multipart form. Fields: file (required, 5-30s audio), name (required), language (optional, default en), model (optional — auto-picks cosyvoice2 for zh/ja/ko else openvoice), consent_confirmed (required, any truthy value).

curl -X POST https://tts.ai/api/v1/user-voices/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -F "file=@reference.wav" \
  -F "name=My Narrator" \
  -F "language=en" \
  -F "consent_confirmed=true"

# Response:
{
  "public_id": "uv_a1b2c3d4e5f6",
  "id": 42,
  "name": "My Narrator",
  "model_name": "openvoice",
  "language": "en",
  "reference_audio_url": "https://tts.ai/media/user-voices/....wav",
  "storage_status": "active",
  "created_at": "2026-04-17T03:45:00+00:00"
}

Lo àwòrán tí a fi pamọ́ nínú TTS

POST sí /api/v1/tts/ (ÌṢẸ: wẹ́ẹ̀bù VPS ààyè, kò jẹ́ api.tts.ai) láti inú àwọn_àwòrán_àkọ́kọ́. A tí fi àwòrán tí a fi pamọ́ rẹ̀ pamọ́ sí ààyè ìṣàfarawé.

curl -X POST https://tts.ai/api/v1/tts/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -H "Content-Type: application/json" \
  -d '{"text":"Hello from my saved voice","user_voice_id":"uv_a1b2c3d4e5f6"}'

# Returns a queued job — poll /v1/speech/results/?uuid=... for the audio URL.

Àtòjọ/Pamu

GET    https://tts.ai/api/v1/user-voices/           # list your saved voices + quota info
DELETE https://tts.ai/api/v1/user-voices/?public_id=uv_a1b2c3d4e5f6

Àwọn àyọkà ìpamọ́/paṣẹ́ padà (laisí ẹ̀yàn)

Archived voices stay in your account but can't be used in TTS. Useful for dormant end users so your list stays clean.

POST https://tts.ai/api/v1/user-voices/uv_a1b2c3d4e5f6/archive/
POST https://tts.ai/api/v1/user-voices/uv_a1b2c3d4e5f6/reactivate/

Àwọn Ààtòjọ-ẹ̀yàn

Àkọlé sí Àkọ́kọ́

Python - requests

import requests

API_KEY = "sk-tts-your-key"

# Text to Speech
response = requests.post(
    "https://api.tts.ai/v1/tts/",
    headers={"Authorization": f"Bearer {API_KEY}"},
    json={
        "model": "kokoro",
        "text": "Hello from TTS.ai!",
        "voice": "af_bella",
        "format": "mp3"
    }
)

with open("output.mp3", "wb") as f:
    f.write(response.content)

print(f"Credits used: {response.headers.get('X-Credits-Used')}")

Àwọn Àmì-ìwé

Python - requests

# Speech to Text
with open("recording.mp3", "rb") as f:
    response = requests.post(
        "https://api.tts.ai/v1/stt/",
        headers={"Authorization": f"Bearer {API_KEY}"},
        files={"file": f},
        data={"model": "faster-whisper", "timestamps": "true"}
    )

result = response.json()
print(result["text"])

Àwọn Àmì-ìwé

Python - requests

# Voice Cloning
with open("reference.wav", "rb") as ref:
    response = requests.post(
        "https://api.tts.ai/v1/tts/clone/",
        headers={"Authorization": f"Bearer {API_KEY}"},
        files={"reference_audio": ref},
        data={
            "text": "This speech uses a cloned voice.",
            "model": "chatterbox"
        }
    )

with open("cloned_output.mp3", "wb") as f:
    f.write(response.content)

Àkọlé sí Àkọ́kọ́

JavaScript - fetch

const API_KEY = 'sk-tts-your-key';

// Text to Speech
const response = await fetch('https://api.tts.ai/v1/tts/', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${API_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'kokoro',
    text: 'Hello from TTS.ai!',
    voice: 'af_bella',
    format: 'mp3'
  })
});

const audioBlob = await response.blob();
const audioUrl = URL.createObjectURL(audioBlob);
const audio = new Audio(audioUrl);
audio.play();

Àwọn Àmì-ìwé

JavaScript - fetch

// Speech to Text
const formData = new FormData();
formData.append('file', audioFile);
formData.append('model', 'faster-whisper');

const response = await fetch('https://api.tts.ai/v1/stt/', {
  method: 'POST',
  headers: { 'Authorization': `Bearer ${API_KEY}` },
  body: formData
});

const result = await response.json();
console.log(result.text);

Àkọlé sí Àkọ́kọ́

cURL

# Text to Speech
curl -X POST https://api.tts.ai/v1/tts/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"kokoro","text":"Hello!","voice":"af_bella","format":"mp3"}' \
  -o output.mp3

Àwọn Àmì-ìwé

cURL

# Speech to Text
curl -X POST https://api.tts.ai/v1/stt/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -F "file=@recording.mp3" \
  -F "model=faster-whisper" \
  -F "timestamps=true"

Àwọn Àmì-ìwé

cURL

# Voice Cloning
curl -X POST https://api.tts.ai/v1/tts/clone/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -F "reference_audio=@reference.wav" \
  -F "text=This uses a cloned voice." \
  -F "model=chatterbox" \
  -o cloned.mp3

Àwọn ìṣàfarawé àwòrán

cURL

# Audio Enhancement
curl -X POST https://api.tts.ai/v1/audio/enhance/ \
  -H "Authorization: Bearer sk-tts-your-key" \
  -F "file=@noisy_audio.mp3" \
  -F "denoise=true" \
  -F "enhance_clarity=true" \
  -o enhanced.mp3

Àwọn Àmì-ìwé Àṣìṣe

Àwọn àṣìṣe gbogbò náà ń fi àwọn àgbékalẹ̀ JSON pamọ́ sí error Àwọn ààyè-iṣẹ́

Àwọn Àwọn Àkọ́gbégbé

{
  "error": {
    "code": "insufficient_credits",
    "message": "You do not have enough characters for this request.",
    "characters_required": 4000,
    "characters_available": 2000
  }
}

Ààyè HTTP	Àwọn Àṣìṣe	Àkóónú
400	`bad_request`	Àwọn ìpéwọ̀n ìtàn tí kò tọ́. Wòye àkọlé àṣẹ fún àwọn ìròyìn.
401	`unauthorized`	Bọ́tìnì API tí kò wa tàbí kò tọ́.
402	`insufficient_credits`	Kò ní àwọn àmì-àṣírí tòjú. Ràwọ́lù nínú /pricing/.
403	`forbidden`	O kò ní ìṣẹ̀dà láti gba ààyè-iṣẹ́ yìí (gẹ́gẹ́ bíi, ìṣàfihàn iṣẹ́ òǹlò mìíràn). Ààyè-iṣẹ́ API ní pàtó nínú àwọn ìṣàmúlò-ètò nípa.
404	`not_found`	A kò rí àwọn ìṣàmúlò-ètò àti àwòrán.
413	`file_too_large`	Àwọn fáìlì tí a fi pamọ́ tí wọ́ inú àwọn ìwọ̀n ìwọ̀n.
429	`rate_limited`	Àwọn ìtàn tí o jù lọ. Ṣayẹwo àwọn àwọn àkọlé àwọn ìdájú àwọn ìṣàmúlò-ètò.
500	`internal_error`	Àṣìṣe àwọn sáà. Wá lẹ́ẹ̀kan nínú ìtàn.
503	`model_loading`	Àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn

Àwọn wẹ́ẹ̀bù

Fún àwọn iṣẹ́ tí n lọ́wọ́lọ́wọ́ jú lọ́wọ́lọ́wọ́ lọ́wọ́lọ́wọ́, o lè ṣàfihàn ààtòjọ-ẹ̀yàn webhook_url. Nígbà tí iṣẹ́ náà bá parí, a á fi ààtòjọ-ẹ̀yàn náà pamọ́ sí URL rẹ̀.

Àwọn Ìṣàmúlò-ètò

{
  "event": "task.completed",
  "task_id": "task_abc123",
  "status": "success",
  "result_url": "https://api.tts.ai/v1/results/task_abc123",
  "credits_used": 12,
  "created_at": "2025-01-15T10:30:00Z",
  "completed_at": "2025-01-15T10:30:45Z"
}

Àwọn àwọn ìṣàmúlò-ètò Webhook tí wa nígbà tí a tí parí. Gẹ́gẹ́ bí a tí wa nígbà tí a bá gba wọn lọ́wọ́lọ́wọ́.

Tí O Tí Ìjánú Rẹ́?

Gba bọ́tìnì API rẹ̀ láti bẹrẹ ìdapọ TTS.ai nínú àwọn ìṣàmúlò-ètò rẹ̀.

Ṣàfihàn Àwọn ìṣàmúlò-ètò

Àkọsílẹ̀ API

Àwọn ìṣàmúlò-ètò

Bọ́tìnì API

URL Ìdálẹ̀

Àwọn Àmì-ìwé

Àwọn Ìṣàmúlò-ètò

Àwọn SDK

Python

JavaScript / Node.js

URL Ìdálẹ̀

Àwọn Ìdálẹ̀ Ìjánu-ìṣàmúlò-ètò

Àwọn Ìṣàmúlò-ètò

Àkọlé sí Àkọ́kọ́

Àwọn ìṣàmúlò-ètò

Àwọn ìṣàmúlò-ètò

Àwọn àmì-ìwé SSML

Àwọn ìsàlẹ̀-ilà

Step 1: Submit request

Step 2: Poll for result

Step 3: Download audio

Full example

Àwọn Àmì-ìwé

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìsàlẹ̀-ilà

Àwọn Àmì-ìwé

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìsàlẹ̀-ilà

Àtòjọ-ẹ̀yàn Àwọn Àmì-ìwé

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìṣàmúlò-ètò

Àwọn ìsàlẹ̀-ilà

Àwọn ìṣàfarawé kọ̀ǹpútà

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìsàlẹ̀-ilà

Àwọn Àkọlé

Àwọn ìṣàmúlò-ètò (multipart/form-data)

Àwọn ìsàlẹ̀-ilà

Àwọn Àtòjọ-ẹ̀yàn Àkọsílẹ̀

Àkọlé àwòrán

Àwọn ìṣàmúlò-ètò (multipart/form-data tabi JSON)

Àwọn ìsàlẹ̀-ilà

Àwọn àwọn àwọn àwọn àwọn

Àwọn Àtòjọ-ẹ̀yàn

Àwọn ìsàlẹ̀-ilà

Ìṣàfilọ́lẹ̀ Àwọn Àmì-ìwé

Àwọn Àtòjọ-ẹ̀yàn

Àwọn ìsàlẹ̀-ilà

Àwọn Àwọn Ààyè-iṣẹ́

Àwọn ìsàlẹ̀-ilà

Àtòjọ àwọn ìṣàmúlò-ètò

Àwọn ìsàlẹ̀-ilà

Àwọn Àmì-ìwé Àtòjọ

Àwọn Àlàyé Àwọn Àwọn Ààtò

Àwọn ìsàlẹ̀-ilà

Àwọn àkọlé (SRT / VTT) new

Àwọn Àlàyé Àwọn Àwọn Ààtò

Àwọn Àwọn Àkọlé new

Àwọn ìṣàmúlò-ètò (POST)

Àwọn Àkọlé new

Àwọn Àtòjọ-ẹ̀yàn

Àwọn Àwọn Àtòjọ-ẹ̀yàn

Àwọn Àwòrán Tí A Fi Pamọ́ (Àwọn Kọlọ̀nì Tí A Fẹ̀)

Fi àwòrán pamọ́

Lo àwòrán tí a fi pamọ́ nínú TTS

Àtòjọ/Pamu

Àwọn àyọkà ìpamọ́/paṣẹ́ padà (laisí ẹ̀yàn)

Àwọn Ààtòjọ-ẹ̀yàn

Àkọlé sí Àkọ́kọ́

Àwọn Àmì-ìwé

Àwọn Àmì-ìwé

Àkọlé sí Àkọ́kọ́

Àwọn Àmì-ìwé

Àkọlé sí Àkọ́kọ́

Àwọn Àmì-ìwé

Àwọn Àmì-ìwé

Àwọn ìṣàfarawé àwòrán

Àwọn Àmì-ìwé Àṣìṣe

Àwọn wẹ́ẹ̀bù

Tí O Tí Ìjánú Rẹ́?