ጽሑፍ ናብ ቃላት መራኸቢታት ሙዚቃ ድምጺ ናብ ጽሑፍ ድምጺ ድምጺ ገበን ተጨማሪ
ረቛሒታት / መተግበሪያታት

ሰነድ

TTS.ai ኣብ ኣፕሊኬሽናትካ ምስ REST APIና ተሓታቲፍካ ምዝገባ። OpenAI-compatible format for easy migration.

REST API OpenAI ተዛማዲ መልሲ JSON ደገፍ ስትሪሚንግ

ግምገማ

እቲ TTS.ai API ንኹሉ ባህርያት ናይቲ መተግበሪ ብፕሮግራም ክኸይድ ይሕግዘካ እዩ። እዚ ማለት፡ ፅሑፍ-እቲ-ብቓል-ዝሕብር፣ ቓል-እቲ-ብቓል-ዝሕብር፣ ድምጺ-ዝሕብር፣ ድምጺ-ዝዕብል፣ ወዘተ.

ምትካል

ረክብ ሻዕብያ APIካ ካብ ቍጽሪ ኣድራሻ. ኣብ ኩሉ ልምዓት ተቐባልነት ዘለዎ፣ ነጻ ኣድራሻታት ጨምሮ።

መሰረታዊ URL

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

ምዝገባ

ናጽነት Authorization ርኢቶ

ምስክር ወረቐት

ነጻ ደረጃ — መሰረታዊ መሳርሒ ኣይተጠቕሰን። ኣነ /v1/tts/ ሰርሕ ብነጻ (piper, vits, melotts, kokoro). ምዝገባ ን 15,000 ተጨማሪ ገጽታዎችን መዳረሻን ለፕሪሚየም ሞዴሎች ለማግኘት ነጻ ምዝገባን ምዝገባን.

ንሞዴላት ተለፎን Premiumን ዝለዓለ ርክብ ቴሌፎንን፣ ምስ ቶኬን ተሳተፊ ኣብ Authorization ርኢቶ.

ርኢቶ HTTP 
Authorization: Bearer sk-tts-your-api-key-here
ሻዕብያ APIካ ረሲዕካ ርኣዮ። ኣብ ክሊንት-ሳይድ ኮድ፣ ኣብ ደገፍታት ህዝባውያን፣ ወይ ኣብ መዝገብታት ኣይተኸፋፍልን። ኪስታት ብቐንዱ ካብ ኣድራሻኻ ምቕራብ ሒዝካ ሒ

SDKs

TTS.ai ኣብ ኣፕሊኬሽንካ ንምእታው TTS.ai ኣብ TTS.ai ንምእታው TTS.ai ኣብ ኣፕሊኬሽንካ ንምእታው TTS.ai ኣብ TTS.ai ንምእታው TTS.ai ኣብ TTS.ai ንምእታው

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

መሰረታዊ URL

መሰረታዊ URL: https://api.tts.ai/v1/

ኵሎም መጨረሻታት ርሒቖም እዮም ናብዚ መሰረታዊ URL'ዚ ዝድግፉ። ለምሳሌ፡ መጨረሻ TTS እዩ፦

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

ቍጽሪ

API ፍጥነት ወሰናት ብፕላን ይለያዩ:

ደብዳቤ ደብዳቤታት/ሚን ተመሳሳሊ ርዝመት ጽሑፍ
ነጻ 10 2 500 ቃላት
መጀመርታ 30 3 1,000,000 ቃላት
ረቂቕ 60 5 1,000,000 ቃላት
ንግዲ 300 20 50,000 ቃላት

ርዝመት X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset.

ቍጽሪ ኣርእስቲ

ሰርቪስ ዋጋ ቍጽሪ
TTS (ብነጻ ሞዴላት: Piper, VITS, MeloTTS) 1,000 ኣርእስቲ ኣብ 1,000 ኣርእስታት
TTS (ስታንደርድ ሞዴላት: Kokoro, CosyVoice 2, ወዘተ.) 2,000 ኣርእስቲ ኣብ 1,000 ኣርእስታት
TTS (Premium models: Tortoise, Chatterbox, etc.) 4,000 ኣርእስቲ ኣብ 1,000 ኣርእስታት
ድምጺ ናብ ጽሑፍ 2,000 ኣርእስቲ ድምጺ
ድምጺ 4,000 ኣርእስቲ ኣብ 1,000 ኣርእስታት
ድምጺ ምትኻን 3,000 ኣርእስቲ ድምጺ
ድምጺ 2,000 ኣርእስቲ ድምጺ
ድምጺ ምውጻእ / ድምጺ ምፍጣር 3,000-4,000 ኣርእስቲ ድምጺ
ትርጉም ቃላት 5,000 ኣርእስቲ ድምጺ
ድምጺ 3,000 ኣርእስቲ ሒደት
Key & BPM Finder ነጻ --
ድምጺ ምትኻን ነጻ --

ጽሑፍ ናብ ቃላት

POST /v1/tts/

ጽሑፍ ናብ ቃላት ድምጺ ይወሃብ። ድምጺ ፋይል ኣብ ዝደሊ ቅርጽ ይቕረቡ።

ቍጽሪ ደብዳቤ

ቍጠባዊዓይነትዝግባእመግለጺ
model string ኣይ ሞዴል ID (e.g., ቍጽሪ, ቻትቦክስ, ፒፐር). እንተ ተቐቢሉ፣ ብተደጋጋሚ ናጻ ሞዴል ንረክብ፣ እቲ ዝረኸብካዮ ቋንቋ — ቍጽሪ for en/ja/zh/ko/fr/de/it/pt/es/hi/ru, ፒፐር ንኻልኦት ቋንቋታት ዝደገፍ (ar/pl/nl/cs/da/fi/el/hu/tr/uk/vi/etc.).
text string ኣየ ጽሑፍ ንምውጻእ ናብ ቃላት. 500 ኣሃዝታት (ነጻ ኣድራሻ) 5,000 (ነጻ ኣድራሻ) 1,000,000 (ተኸፊሉ)
voice string ኣየ ድምጺ ID (ጥቕሲ) /v1/voices/ (to list available voices)
format string ኣይ ቅርጽ ምርካብ: mp3 (ተቐባልነት) wav, FLAC, ogg
speed float ኣይ መብዛሕትኡ ግዜ 1.0ርክብ 0.5 ርክብ 2.0
language string ኣይ ኮድ ቋንቋ (e.g., ፊደል(_F), ሱዳን). ብኻልእ መገዲ ይርከብ እንተ ተቐቢሉ
instructions string ኣይ ተግባር/ምቕጻል ድምጺ (≤500 ቃላት)፣ ምሳ. \
pronunciations object | array ኣይ ድምጺ ብጠለብ ዝቐየረ. ወይ }
stream boolean ኣይ ምላሽ ስትሪም ምፍጣር ምፍጣር ሓሶት

ምሳሌ

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

SSML መለክዒታት

ቍጽሪ፣ ዕለት፣ ኣመዛዛቢ ገንዘብ፣ ቍጽሪ ስልኪ፣ ቍጽሪ ፊደልን መዝገበ ቃላትን ሒዝካ

ተርጓሚምዝገባተዛረበ
cardinal1234one thousand two hundred thirty-four
ordinal21twenty-first
date1999-12-31ነሓሰ 31, 1999
time14:30two thirty PM
telephone+1-555-867-5309plus one five five five eight six seven…
currency$1,234.56one thousand two hundred thirty-four dollars and fifty-six cents
spell-outNASAN A S A

ቀን ሜዳ ቛንቋ እንግሊዝኛ dmy ኣብ ካልእ ቦታ; ተጻሒፉ ቅርጺ

ምሳሌ 
{
  "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."
}

መልሲ

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.

ምሳሌ ሙሉ

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.

ድምጺ ናብ ጽሑፍ

POST /v1/stt/

ድምጺ ናብ ጽሑፍ ሒዝካ ተርእዮ። 99 ቋንቋታት ይደግም

ቍጽሪ ደብዳቤ (multipart/form-data)

ቍጠባዊዓይነትዝግባእመግለጺ
file file ኣየ ፋይል ድምጺ (MP3, WAV, FLAC, OGG, M4A, MP4, WebM)
model string ኣይ ቍጽሪ ሞዴል: ድምጺ (ተቐባልነት) ፋስተር-ዊስፐር, sensevoice
language string ኣይ ኮድ ቋንቋ ኣቶ ንኡስ-መዳርግቲ
timestamps boolean ኣይ ቍጽሪ ግዜ ኣብ ደረጃ ቃል ኣውጽእ። ሓሶት
diarize boolean ኣይ ድምጺ ድምጺ ምፍጣር ምፍጣር ሓሶት

መልሲ

መልሲ 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"
    }
  ]
}

ድምጺ

POST /v1/tts/clone/

ቃላት ኣብ ሓደ ክሎነድ ድምጺ ሒዝካ ምጽሓፍ። ድምጺ ርኢኻን ጽሑፍን ኣትዉ።

ቍጽሪ ደብዳቤ (multipart/form-data)

ቍጠባዊዓይነትዝግባእመግለጺ
reference_audio file ኣየ ድምጺ ረድኤት (10-30 ሰከንድ ዝውሰድ) 20MB ማይክሮ
text string ኣየ ጽሑፍ ንምብጻሕ ኣብ ክሎነድ ድምጽ
model string ኣይ ቍጽሪ ቍጽሪ: ቻትቦክስ (ተቐባልነት) ድምጺ 2, gpt-sovits
format string ኣይ ቅርጽ ምርካብ: mp3 (ተቐባልነት) wav, FLAC
language string ኣይ ኮድ ቋንቋ-መዳርግቲ. እቲ ዝተመርጸ ሞዴል ክሕብር ኣለዎ

መልሲ

ፋይል ድምጺ ከም ባንየር ሓበሬታ ይቕረቡ፣ ከምኡ'ውን ከም TTS መጨረሻ-ድግሪ

ድምጺ ምትኻን

POST /v1/voice-convert/

ድምጺ ንምውዳቕ፡ ከም ካልእ ድምጺ ይሰማማዕ። ድምጺ መነባብሮ ኣትዉን ድምጺ መዳርግቲ ይምረጡ።

ቍጽሪ ደብዳቤ (multipart/form-data)

ቍጠባዊዓይነትዝግባእመግለጺ
file file ኣየ ፋይል ድምጺ መነባብሮ (MP3, WAV, FLAC). 50MB ማይክሮፎን
target_voice string ኣየ ድምጺ ID ንምውጻእ (ሕተት) /v1/voices/ (to list available voices)
model string ኣይ ድምጺ ምትካል ሞዴል: openvoice (ተቐባልነት) knn-vc
format string ኣይ ቅርጽ ምርካብ: wav (ተቐባልነት) mp3, FLAC

ምሳሌ

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

መልሲ

ፋይል ድምጺ ከም ብሉይ መዝገብ ይቕበል

ትርጉም ቃላት

POST /v1/speech-translate/

ድምጺ ዝተዛረበ ካብ ቋንቋ ናብ ካልእ ቋንቋ ተርጒም። ኣብ ሓደ ጥዕና ቃለ-መሕትት ቃለ-መሕትት-ክኢላ፣ ትርጉም፣ን ጽሑፍ-ክኢላ-ክኢላ ይዛረብ።

ቍጽሪ ደብዳቤ (multipart/form-data)

ቍጠባዊዓይነትዝግባእመግለጺ
file file ኣየ ድምጺ ፋይል ኣብ ቋንቋ መረጋገጺ. Max 100MB.
target_language string ኣየ ኮድ ቋንቋ-መዳርግቲ (e.g. ሱዳን, ፊሊፒንስ, de, ኣየ)
voice string ኣይ ድምጺ ንምትርጉም ምርጫ. ብቐንዱ ከተምሃር እንተዘይከኣለ
preserve_voice boolean ኣይ ድምጺ መሰረታዊ ተናጋሪ ንምሕላው ይጥምት። ሓሶት

መልሲ

መልሲ 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
}

ድምጺ ናብ ድምጺ

POST /v1/speech-to-speech/

ስነ-ጥበብ ቃላት፣ ስነ-ሓሳብ፣ ወይ ስነ-ጽሑፍ ኣብ ዝቕጽል እዋን ቐይድ። ንድምጺ፣ ፍጥነት፣ንጽሑፍነት ንምድላው ጠቃሚ እዩ።

ቍጽሪ ደብዳቤ (multipart/form-data)

ቍጠባዊዓይነትዝግባእመግለጺ
file file ኣየ ፋይል ድምጺ ቃላት መነባብሮ. Max 50MB.
voice string ኣየ ድምጺ ID ናይ'ቲ ድምጺ ምርካብ
model string ኣይ ቍጽሪ: openvoice (ተቐባልነት) ቻትቦክስ
emotion string ኣይ ስነ-ሓሳብ ነጻ, ሐዲስ, ሐዘን, ተሓቲቱ, ተዛሪቡ
speed float ኣይ ርኢቶ 1.0ርክብ 0.5 ርክብ 2.0

መልሲ

ፋይል ድምጺ ከም ብሉይ መዝገብ ይቕበል

መሣሪያታት ድምጺ

ድምጺ ንምፍጣር መጨረሻ-ጥቕዓት ንምድጋፍ፣ ድምጺ ንምውጻእ፣ ደምቢ ንምፍጣር፣ንሕሉፍ

POST /v1/audio/enhance/

ድምጺ ረክብ: ድምጺ ረክብ፣ ግልጽነት ረክብ፣ ረቛሒ

file fileድምጺ ፋይል ንምዕዋት
denoise booleanድምጺ ምቕያር ኣድላዪ (ተቐዳዲሙ: ሓቂ)
enhance_clarity booleanድምጺ
super_resolution booleanድምጺ ረኺብካ (ምስ ዝቐረበ: ሓሶት)
strength integer1-3 (ጥቕሚ፡ መሓመድ፡ ብርቱዕ)። ዘይምሕሳብ፡ 2
POST /v1/audio/separate/

ድምጺ ካብ መሳርሒታት ምፍጣር (ድምጺ ምፍጣር) ወይ ድማ ናብ ቅርጺ ምፍጣር።

file fileድምጺ ፋይል ንምቕራብ
model stringdemucs (default) ወይ spleeter
stems integerቍጽሪ ቅርጽታት: 2, 4, 5, ወይ 6 (ኣቐዲሙ: 2)
format stringቅርጽ ምርካብ: wav, mp3, FLAC
POST /v1/audio/dereverb/

ድምጺ ካብ ድምጺ መዝገብታት ሒዝካ ምውጻእ

file fileድምጺ ፋይል ንምሕላው
type stringecho or reverb (default: both)
intensity integer1-5 (default: 3)
POST /v1/audio/analyze/ ነጻ

ድምጺ ንምፍታሕ ድምጺ ክተመርመር፣ BPM፣ን ድምጺ ሒደት

file fileድምጺ ፋይል ንምፍታሕ
መልሲ
{
  "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/ ነጻ

ድምጺ ኣብ ቅርጽታት ምትሓዝ

file fileድምጺ ፋይል ንምቕያር
format stringቅርጺ ዕላማ: mp3, wav, FLAC, ogg, m4a, aac
bitrate integerናይ ምርካብ ቢትሬት ኣብ kbps: 64, 128, 192, 256, 320
sample_rate integerርዝመት ሰለስተ ሰለስተ
channels stringmono ወይ stereo

ድምጺ

POST /v1/voice-chat/

ድምጺ ወይ ጽሑፍ ኺእክልን መልሲ AI ምስ ቓል ዝተሰነዳ ክረክብን ይኽእል እዩ።

ቍጽሪ ደብዳቤ (multipart/form-data ወይ JSON)

ቍጠባዊዓይነትዝግባእመግለጺ
audio file ኣይ* ድምጺ ምዝገባ (ወይ ድምጺ ወይ ጽሑፍ (ተጠቕሰ)
text string ኣይ* ጽሑፍ ምዝገባ (ወይ ድምጺ ወይ ጽሑፍ (ተጠቕሰ)
voice string ኣይ ድምጺ ንምምላስ AI. ዘይሕጋዊ: ረ_ድእ
tts_model string ኣይ TTS ሞዴል ንምምላስ። ዘይሕጋዊ፡ ቍጽሪ
system_prompt string ኣይ ናይ ባዕሉ ስርዓት ፕሮም
conversation_id string ኣይ ቀጥል የድሊ ቃለ-መጠይቅ

መልሲ

መልሲ 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
}

መዝገብ ቤት

POST /v1/tts/batch/

ቍጽሪ ቍጽሪ ጽሑፋት ንምቕራብ ንተጻዋእቲ ገጽ

ቍጠባዊ

ቍጠባዊዓይነትመግለጺ
textsarrayArray of objects: {text, model, voice}. Max 50 items.
webhook_urlstringመረጋገጺ URL ን POST ውጽኢት ምስ ሙሉእ

መልሲ

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

ግምገማ ሒዝካዮ ኣትዩ ፡ GET /v1/tts/batch/result/?batch_id=abc123

ድምጺ

POST /v1/voice-embed/

ድምጺ ንምእታው ካብ ረቛሒ ድምጺ መጀመርያ ሒዝዎ። ነቲ embed_id ኣብ ዝለዓለ ድምጺ ክሎን ክኢላታት ንምውጻእ ተጠቒሙ።

ቍጠባዊ

ቍጠባዊዓይነትመግለጺ
filefileReference audio file (WAV, MP3, FLAC).
modelstringCloning model (default: chatterbox). Supported: chatterbox, cosyvoice2, openvoice, gpt-sovits, spark, indextts2, qwen3-tts.

መልሲ

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

ምርመራ ጥዕና

GET /v1/health/

ቍጽሪ GPU ሰረተ-ጽሑፍ፣ ዝተጫወቱ ሞዴላት፣ ከምኡ'ውን መጠን ናይቲ ዑደት ምርኣይ። ምስክር ወረቐት የድልየኩም። 30 ሰከንድ ኣብ ካሽ ተዘርጊሑ።

መልሲ

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

ቍጽሪ ሞዴላት

GET /v1/models/

መዝገብ ናይ ኩሉ ዝርከብ ሞዴላት ምስ ልምምድኦም ይቕረ በለ።

መልሲ

መልሲ 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
    }
  ]
}

ድምጺታት ዝርዝር

GET /v1/voices/

ድምጺታት ረኺብካዮም ርኢኻ፣ ብሞዴል ወይ ቋንቋ ተቐቢልካ

ርኢቶ

ቍጠባዊዓይነትመግለጺ
model string ብሞዴል ID ፊልተር (e.g. ቍጽሪ)
language string ብኮድ ቋንቋ ፊልተር (e.g. ፊደል(_F))
gender string ጾታ: ጾታ, ሴት, ነጻ

መልሲ

መልሲ 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
}

መዝገበ ቃላት (SRT / VTT) _አዲስ

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

ሰንሰለታዊ ርኢቶታት ንምምጻእ ን TTS ስራሕ ሙሉእ. Whisper ርኢቶታት ኣብ ድምጺ ይሰርሕን SRT ወይ WebVTT ይቕበልን። ውጽኢት ኣብ ዲስክ ይቕመጥ፡ ከምኡ'ውን ሓደ ካልኣይ ጥሪ ንተመሳሳሊ uuid ኣብ ዲስክ ክነብር፡

ርኢቶ

ቍጠባዊዝግባእመግለጺ
uuidኣየUUID ስራሕ ዝተረኽበ ብ /v1/tts/ ወይ /v1/voice-clone/
formatኣይsrt (ተቐባልነት) ወይ vtt.
downloadኣይ1 መላኺ መዝገብ-መዘክሪ ከምኡ'ውን እቲ ብራውዘር ክጥቀመሉ ክኽእል እዩ
languageኣይምትእስሳር ናብ ሞዴል ምትእስሳር (ብተደጋጋሚ እንተተቐየረ)
cURL
curl "https://api.tts.ai/v1/speech/subtitles/?uuid=$UUID&format=srt&download=1" -o subtitles.srt

መዝገበ ቃላት ድምጺ _አዲስ

GET POST DELETE /api/v1/pronunciations/

ንተገልጋሊ TTS ንኸመይ ጌርካ ቃላት ዝንገር ትገልጽ። ዝረኸብካዮ ምዝገባታት ብውሑድ ንየናይ TTS ሕቶ እንተደኣ ረኺብካዮ ይጥቀሙ። 200 ምዝገባታት ኣብ ሓደ ኣድራሻ ምዝገባ ወሰነ ኣሎ።

ቍጽሪ ደብዳቤ (POST)

ቍጠባዊዓይነትመግለጺ
wordstringቃል ንምልላይ (e.g. GIF, ስነ-ጥበባዊ). ቃል-ግዳም ተዛረበ።
replacementstringከመይ ጌርካ ክትጽሕፎ ትኽእል ኢኻ (e.g. jiff, ann THROP ick)
languagestringኣልቦ = ንዅሉ ቋንቋታት ይጥቀም።
case_sensitivebooleanኣቐዲሙ ሓሶት. ምትእስሳር ናይ ፊደል መጠን ልክዕ ኣብ ሓቂ.
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 ድምጺ ኣብ /v1/tts/ ክጥቀመሉ ይኽእል እዩ፣ ከም ሓደ ኣርእስቲ ወይ ከም ሓደ ኣረኣእያ (ኣብ TTS endpoint parameters ተመልከት)

ደራሲ ጽሑፍ _አዲስ

ሒዝካ