Àwọn Àkọlé àti Àwọn Àkọlé

Build voice-enabled applications with our REST API. Add natural text-to-speech, voice cloning, speech-to-text, and audio processing to your apps, chatbots, voice assistants, and SaaS products. OpenAI-compatible format, 20+ models, simple integration.

API REST Àwọn Àkọ́gbégbé Àwọn Ìṣàmúlò-ètò Àkọ́kọ́ Àwọn Àṣẹ Ìṣàmúlò-ètò

Àtòjọ-ètò TTS Fẹ́ẹ̀lì Àwọn Àkọsílẹ̀ API

_Yanju

0/500

Free pẹlu Kokoro, Piper, VITS, MeloTTS

Àwọn àwòrán tí o ti ṣẹ̀dà tí o bá han níbẹ̀

Ṣí àwọn àyọkà ìṣàmúlò-ètò TTS kíki

Àwọn Àbùdá API fún Àwọn Àkọlé

Gbogbo ohun ti o nilo lati kọ́ àwọn ìṣàmúlò-ètò ìṣàfilọ́lẹ̀-ìrọ̀

Àwọn Ìṣàfilọ́lẹ̀

Àwọn ìṣàmúlò-ètò POST kan láti ṣẹ̀dà àkọlé. Àwọn ìṣàmúlò-ètò JSON, àwọn ìṣàmúlò-ètò àwòrán. Àwọn ìṣàmúlò-ètò àti àwọn ìṣàmúlò-ètò HTTP.

OpenAI-Compatible

Àwọn ìṣàmúlò-ètò tí a fi pamọ́ fún OpenAI TTS API. Sún àwọn bọ́tìnì base_url àti API rẹ̀ lọ́wọ́lọ́wọ́ - àwọn ìṣàmúlò-ètò tí wa nígbá tí wọn bá ṣiṣẹ́.

Àwọn ìṣàmúlò-ètò Tí Wá

Access every model through a single API. Switch models by changing one parameter. Compare quality, speed, and cost.

Àwọn ààyè-iṣẹ́

Kokoro kọ́ àwòrán nínú ìsẹ́ẹ̀tì 1. Ó jẹ́ ìṣàfihàn fun àwọn àkọlé àwòrán, àwọn awáròyìn àwòrán, àti àwọn ìṣàmúlò-ètò ìṣàfihàn.

Àwọn Àwọn Àmì-ìwé

Klọ́nọ̀ọ̀kan àwọn ìrànwọ́ láti inú àwọn ààyè-iṣẹ́ ìṣàmúlò-ètò àìpẹ̀ láti inú API. Lo àwọn ìrànwọ́ àìpẹ̀ láti inú àwọn ìṣàmúlò-ètò ìṣàfarawé kọ̀ǹpútà láti inú àwọn ìṣàfarawé kọ̀ǹpútà ìṣàfarawé.

Àwọn ìrísí-lẹ́tà mìíràn

Àwọn ìṣàfilọ́lẹ̀ bí WAV, MP3, OGG, tàbí FLAC. Yan àwọn ìṣàmúlò-ètò àti ìfẹ̀sí bítì. Àwọn ìṣàfilọ́lẹ̀ ìṣàmúlò-ètò ìṣàfilọ́lẹ̀ ìgbọ̀n fún àwọn ìṣàmúlò-ètò ìgbárábọ̀.

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

Yan módè́lì tò tọ́ fún ìrànwọ́, ìṣàmúlò-ètò rẹ̀, àti àwọn ìṣàmúlò-ètò àwọn owó

Kokoro

Free

Lightweight 82M parameter model delivering studio-quality speech with blazing-fast inference.

Fast 5/5

Ó dara jù fún: Móòdù àìpẹ̀ jú — àìpẹ̀ ìsàlẹ̀-ilà ìsàlẹ̀-ilà ìsàlẹ̀-ilà, tí a fẹ́ fún àwọn ìṣàmúlò-ètò àti àwọn chatbots

Àwọn ààyè-iṣẹ́ Kokoro

CosyVoice 2

Standard

Alibaba's scalable streaming TTS with human-parity naturalness and near-zero latency.

Medium 5/5 Àwọn Àmì-ìwé

Ó dara jù fún: TTS tí a fi pamọ́ láti fi àwọn ìṣàmúlò-ètò ìrànwọ́ àwọn awáròyìn àwòrán sọrọ̀

Àwọn ààyè-iṣẹ́ CosyVoice 2

Sesame CSM

Premium

Conversational speech model generating natural dialogue with appropriate timing and emotion.

Slow 5/5

Ó dara jù fún: AI ibaraẹnisọrọ pẹlu àwọn ààyè-ìṣàmúlò-ètò ìṣàfarawé-ìṣàmúlò-ètò àti àwòrán aṣàwákiri

Àwọn ààyè-iṣẹ́ Sesame CSM

Piper

Free

A fast, local neural text to speech system optimized for Raspberry Pi and embedded devices.

Fast 3/5

Ó dara jù fún: Àwọn àwọn ìṣàmúlò-ètò CPU-ìwọ̀n, àwọn ìṣàmúlò-ètò tí a fi pamọ́ fun àwọn ìṣàmúlò-ètò ìpele-òkè nípa àwọn owó ifowopamọ́ kò ní

Àwọn ààyè-iṣẹ́ Piper

Bark

Standard

Transformer-based text-to-audio model that generates realistic speech, music, and sound effects.

Slow 4/5

Ó dara jù fún: Ìṣàfilọ́lẹ̀ àwòrán láti inú àwọn ìṣàmúlò-ètò ìṣàfarawékọ́ àti ìṣàfilọ́lẹ̀ ìṣàfarawékọ́

Àwọn ààyè-iṣẹ́ Bark

Bii o ṣe le Ṣàfikún TTS API

Lati iforukọsilẹ si ipe API akọkọ ni isalẹ awọn iṣẹju 5

Gba àwọn àwọn àmì-ìwé API Rẹ̀

Ṣẹ̀dà fún ọ̀fẹ̀ àti ìṣàfilọ́lẹ̀ bọ́tìnì API láti inú àwọn àwọn àmì-ìwé rẹ̀. Àwọn àmì-ìwé 15,000 nínú.

Fi Ìsàlẹ̀ Àìpẹ̀ Rẹ̀

POST sí /v1/tts láti inú àkọlé, àwọn módè́lì, àti àwòrán. Gba àwọn báyítì àwòrán padà. Láìnì 5 láti inú ìṣàmúlò-ètò.

Yan àwòrán rẹ

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 àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn àwọn

Fikún sí Ìṣàmúlò-ètò

Sọ́kàn láti fi-ìgbà-nípa-ìgbà-ìgbà-ìgbà-ìgbà-ìgbà. Kò ní àwọn ìgbà ìgbà ìgbà ìgbà. Ṣàyẹwo ìlò nínú àwọn ààyè-iṣẹ́ rẹ̀.

Àwọn Ààyè-iṣẹ́ Àwọn Àkọ́kọ́ Ìṣàmúlò-ètò

Iṣakoso TTS.ai ni eyikeyi ede pẹlu API REST wa

Python Àwọn Àkọ́gbégbé

import requests

response = requests.post(
    "https://api.tts.ai/v1/tts",
    json={
        "text": "Hello from my app!",
        "model": "kokoro",
        "voice": "af_heart",
        "format": "mp3"
    },
    headers={
        "Authorization": "Bearer sk-tts-xxx"
    }
)

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

JavaScript (Node.js) Node.js

const response = await fetch(
    "https://api.tts.ai/v1/tts",
    {
        method: "POST",
        headers: {
            "Content-Type": "application/json",
            "Authorization": "Bearer sk-tts-xxx"
        },
        body: JSON.stringify({
            text: "Hello from my app!",
            model: "kokoro",
            voice: "af_heart",
            format: "mp3"
        })
    }
);

const audio = await response.blob();

cURL Àwọn àwọn àwọn àwọn àwọn àwọn

curl -X POST https://api.tts.ai/v1/tts \
  -H "Authorization: Bearer sk-tts-xxx" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from my app!",
    "model": "kokoro",
    "voice": "af_heart",
    "format": "mp3"
  }' \
  --output output.mp3

Àwọn ìgúnrégé AI-Ìṣàfihàn Àwọn àgbéwọlé

# Works with OpenAI client library
from openai import OpenAI

client = OpenAI(
    api_key="sk-tts-xxx",
    base_url="https://api.tts.ai/v1"
)

response = client.audio.speech.create(
    model="kokoro",
    voice="af_heart",
    input="Hello from my app!"
)

response.stream_to_file("output.mp3")

Get Your Free API Key

Ohun ti Àwọn Àkọlé àwòrán Fi TTS.ai

Àwọn ìṣàmúlò-ètò àti àwọn ìṣàmúlò-ètò ìdáràn

Àwọn Àkọlé

Fi àwọn àgbéwọlé ìsàlẹ̀-ilà ìranlọwọ AI rẹ̀ àti àwọn ìsàlẹ̀-ilà àwọn ìṣàfilọ́lẹ̀ rẹ̀ pamọ́. Ṣàfikún àwọn àgbéwọlé LLM láti inú TTS fún àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀. Kokoro náà náà àwọn ìṣàfilọ́lẹ̀ ìsàlẹ̀-ilà ìgbá tí a bá kọ́kọ́. Sesame CSM náà náà àwọn ìsàlẹ̀-ilà ìsàlẹ̀-ilà àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfilọ́lẹ̀ àwọn ìṣàfi

Àwọn ìṣàfihàn LLM sí àwọn ìṣàfihàn àkọlé
Ìjánu-ìjánú ààyè-iṣẹ́ àti Kokoro
Àwọn àkọlé àkọlé láti Sesame CSM
Àwọn ìṣàfihàn àwòrán

Àwọn Ìṣàmúlò-ètò Àkọ́kọ́

Build voice-enabled mobile apps, accessibility tools, reading apps, and language learning platforms. Our REST API works with any mobile framework. Download audio files or stream directly to the client.

React Native, Flutter, Swift, Kotlin
Àwọn Ìṣàmúlò-ètò Ìṣàmúlò-ètò Ìṣàfilọ́lẹ̀
Àwọn àwọn ààyè-iṣẹ́ ìṣàfilọ́lẹ̀ ìṣàfilọ́lẹ̀
Àwọn àwọn ìṣàmúlò-ètò àwòrán

Àwọn Àṣẹ

Àwọn ìṣẹ̀dá àwọn ìròyìn àwọn àwọn ohun-ìṣàfilọ́lẹ̀ àwọn àwọn ohun-ìṣàfilọ́lẹ̀ àwọn àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀ àwọn ohun-ìṣàfilọ́lẹ̀

Àwọn àbùdá ìrànwọ́ àwọn àmì-ìwé
Kò ní àwọn ààyè-iṣẹ́ GPU tí a fẹ́
Ìṣàmúlò-ètò
20+ awọn awoṣe lati fun awọn olumulo rẹ

Àwọn àgbékalẹ̀ ìṣàfarawé

Integrate voice generation into CI/CD pipelines, content automation, and batch processing workflows. Generate thousands of audio files from spreadsheet data, automate podcast production, or build content localization pipelines.

Ìṣàmúlò-ètò àwọn àwọn ààyè-iṣẹ́
Àwọn ààyè-iṣẹ́ ìṣàfihàn àwọn ìṣàfihàn
Ìdákọ́ CI/CD
Àwọn àwọn ààtòjútó àwọn àwọn àwòrán

View Full API Documentation

Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn

Tí a kọ̀ fún àwọn ìṣàmúlò-ètò ìṣàfilọ́lẹ̀

20+

Àwọn Àwọn Àwòrán TTS

100+

Àwọn Àmì-ìwé

30+

Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn Àwọn

<1s

Ìgbà ìtàn (Kokoro)

Àwọn Àtòjọ-ẹ̀yàn

Àwọn ibeere àwọn ìṣàfilọ́lẹ̀ TTS.ai API

Ya. API wa tẹle ìṣàmúlò-ètò àwọn àkọlé OpenAI. Tí o bá lò àwọn àwọn láìbòójútó klìǹẹ̀tì OpenAI Python tàbí JavaScript, o lè yipada sí TTS.ai láti fi àwọn àwọn àpàràmúlò-ètò base_url àti api_key. Àwọn àwọn ìṣàmúlò-ètò rẹ̀ tí wa nípa ìṣàmúlò-ètò.

Kokoro generates audio in under 1 second for typical sentences. CosyVoice 2 supports streaming output for even lower perceived latency. For chatbots and voice assistants, total round-trip time is typically 1-3 seconds depending on text length and model choice.

Awọn awoṣe ọfẹ (Kokoro, Piper, VITS, MeloTTS) jẹ ọfẹ patapata. Awọn awoṣe Standard lo awọn aami 2x fun 1K ti ọrọ. Awọn awoṣe Premium lo awọn aami 4x fun 1K ti ọrọ. Ṣabẹwo ọfẹ pẹlu awọn aami 15,000. Awọn iṣẹ bẹrẹ ni $ 9 / oṣu fun awọn aami 500,000.

Ya. Ṣàfihàn ààyè-iṣẹ́ ìṣàmúlò-ètò àwòrán (5-30 àkókò) sí ààyè-iṣẹ́ ìṣàmúlò-ètò ìṣàfihàn àwòrán, láti lò àtòjọ àwòrán ìṣàfihàn àwòrán nínú àwọn ìṣàfihàn TTS tókàn. Àwọn módè́ẹ̀lì tí wọ́n sáà ìṣàfihàn àwòrán ni CosyVoice 2, Chatterbox, Fish Speech, àti GPT-SoVITS.

Àwọn ìpele àìfẹ́fẹ́ ní àwọn ìdájú àwọn ìṣàmúlò-ètò ìpelé ìpelé (3 àwọn ìtàn nínú ààyè-iṣẹ́ nínú àwọn ààyè-iṣẹ́). Àwọn ìṣàmúlò-ètò tí a pàyà ní àwọn ìdájú àwọn ìṣàmúlò-ètò ìṣàfihàn. Jẹ̀ láti bà wà kọ́ nípa àwọn ìṣàmúlò-ètò ìpelé ile-iṣẹ́.

WAV (kò ní ìṣàmúlò-ètò, ìgúnrégé tí o ga jú lọ), MP3 (ní ìṣàmúlò-ètò, àwọn fáìlì tó kéré jú), OGG (ìṣàmúlò-ètò mìíràn), àti FLAC (ìṣàmúlò-ètò tí kò ní ìdá. Ṣàfihàn ìṣàmúlò-ètò nínú ìtàn rẹ̀. Àtòjọ-ẹ̀yàn nì WAV nínú ìṣàmúlò-ètò ìṣàmúlò-ètò orílẹ̀ móòdù náà.

Ya. Ṣàfikún TTS API wa pẹlú móòdù ìṣàfihàn-si-àkọ́kọ́ atí LLM láti kọ́ ìṣàfihàn ìrànwọ́ àwọn ìrànwọ́ àwọn ìṣàfihàn-ìrọ̀. Kokoro náà náà gbá àwọn ìṣàfihàn-ìsẹ́ àwọn ìṣàfihàn-ìgbá tí a fẹ́ fun àwọn ìṣàfihàn-ìgbá. CosyVoice 2 náà náà gbá àwọn ìṣàfihàn-ìjánú ìṣàfihàn fún àwọn ààyè-iṣẹ́ àwọn ìṣàfihàn-ìgbà tí a fẹ́.

CosyVoice 2 and Kokoro support streaming audio output where audio chunks are delivered as they are generated. This reduces time-to-first-byte for real-time applications like voice assistants and interactive experiences.

The API returns standard HTTP status codes. Implement exponential backoff for 5xx errors and rate limit responses. For mission-critical applications, add a queue with retry logic. Our API has high uptime but resilient error handling is always recommended.

Ya. Àwọn àwọn ààyè-iṣẹ́ ìparí /v1/wòyè àti /v1/móòdù ń fi àwọn àtòjọ JSON tí àwọn wòyè àti àwọn móòdù tó lè wa nípa àwọn ààyè-iṣẹ́ àwọn meta wọn (ìdárá ìtàn, àwọn ìṣàmúlò-ètò ìṣàmúlò-ètò, àwọn ìṣàmúlò-ètò ìrànwọ́, àwọn ìṣàmúlò-ètò ìṣàfihàn). Lò láti kọ́ àwọn àwọn ìṣàfilọ́lẹ̀ móòdù ìṣàfilọ́lẹ̀ nínú ìṣàmúlò-ètò rẹ̀.

Àwọn àwọn àwòrán ọ̀fẹ́ (Kokoro, Piper, VITS, MeloTTS) jẹ́ àwọn àwọn àwòrán tí a lò nígbà tí wọn jẹ́ ọ̀fẹ́. Jẹ́ àwọn àwòrán ọ̀fẹ́, ki o si yipada sí àwòrán tí a lò nínú ìṣàfilọ́lẹ̀ láti páàsì àwòrán. Kò ní àwọn àwọn àwòrán ìṣàfilọ́lẹ̀ tí a fẹ́.

Àwọn móòdù wà ní ìmọ̀rọ̀ọ̀fẹ́, àti àwọn móòdù wà lè jẹ́ aláàánú. Bíbẹ̀ẹkọ, aláàánú-ara wà ní àwọn ohun-iní GPU tí a fẹ́ (à ló 4x NVIDIA Tesla P40 láti 96GB VRAM tó kù). API náà náà ní aláàánú tí a lè lò láti fi owó pamọ́ láti párá àwọn iṣẹ́ inú ilé.

5.0/5 (1)

Tí o tí fẹ́ kọ̀ nípa Àwọn Àmì-ìwé AI?

Get your free API key and start building. 15,000 characters on signup, free models available, comprehensive documentation.

Ṣàfihàn Wó Àwọn Ìtàn