Papatono API

Ka whakaurua a TTS.ai ki ōna taupānga me a tātau REST API. He āhua ōrite OpenAI mō te hekenga ngāwari.

REST API OpenAI e ōrite ana Ka urupare a JSON Mā te tautoko i te rerenga

Whakamāramatanga

Ka homai e te TTS.ai API te āheitanga papatono ki ngā āhuahira papatono katoa: te whakakotahitanga kupu-ki-rongo, te whakawhitinga reo-ki-rongo, te tārua reo, te whakarei oro, me ētahi atu.

Papamahi API

Ki te whiwhi i tātou kī API mai i Ka taea te whakawātea te kāwanatanga o te kāwanatanga.. Kei te wātea i runga i ngā mahere Pro me Enterprise.

URL taketake

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

Ka whakaaetia

Mā te tohu kaihautū Authorization kaipupuru

Tuakiritanga

E hiahiatia ana e ngā tono API katoa te manatoko mā tētahi tohu Bearer i roto i te Authorization kaipupuru.

HTTP Header
Authorization: Bearer sk-tts-your-api-key-here
Kai te mārama ta tātou kī API. Kāore i te tiritiri i roto i te waehere o te taha o te kaiwhakahaere, i ngā pūtahi tūmatanui, i ngā pūkete rānei. Ka huri tonu ngā kī mai i ōna whakaritenga kāwanatanga.

URL taketake

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

E pā ana ngā wāhi mutunga katoa ki tēnei URL taketake. Hei tauira, ko te wāhi mutunga TTS:

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

Te mokatere o ngā tepe

He rerekē ngā tepe ine API e ai ki te mahere:

Rārangi E hiahiatia ana/min E ōrite ana Te roa rawa o te kupu
Pro 60 5 5,000 ngā pūāhua
Kaupapa 300 20 50,000 ngā pūāhua

Kei roto i ia urupare nga taitapa tepe o te mokatere: X-RateLimit-Limit, X-RateLimit-Remaining, X-RateLimit-Reset.

Ko ngā utu pūtea

Waihoki Ko te utu Waihoki
TTS (ngā tauira wātea: Piper, VITS, MeloTTS) 1 pūpū i ia 1,000 ngā tohu
TTS (ngā tauira paerewa: Kokoro, CosyVoice 2, etc.) 2 ngā uara i ia 1,000 ngā tohu
TTS (Wāhi tauira: Tortoise, Chatterbox, etc.) 4 ngā uara i ia 1,000 ngā tohu
Ka kōrerorerotia te kuputuhi 2 ngā uara i ia minu o te oro
Ko te tāruatanga reo 4 ngā uara i ia 1,000 ngā tohu
Kaitautoko reo 3 ngā uara i ia minu o te oro
Whakarei ake reo 2 ngā uara i ia minu o te oro
Ka tangohia te pūoro / Te whakawehenga pūoro 3-4 ngā uara i ia minu o te oro
Whakamāoritanga kōrero 5 ngā uara i ia minu o te oro
Pāpāho reo 3 ngā uara i ia huringa
Ka kitea te kī BPM Waihoki --
Ka whakarerekētia te oro Waihoki --

Waihoki ki te kōrero

POST /v1/tts/

Ka tahuri te kupu ki te oro reo. Ka hoki te faila oro ki te hanga e hiahiatia ana.

Ka tono te tinana

ParameterKāhuaE hiahiatia anaWhakamāramatanga
model string He Tau tauira (hei tauira, kokoro, chatterbox, piper)
text string He Te kupu hei tahuri ki te kōrero (ki te 5,000 ngā pūāhua mō Pro, 50,000 mō Enterprise)
voice string He Voice ID (ka whakamahia te /v1/voices/ hei whakarārangi i ngā reo e wātea ana)
format string Kāore Kāhua huaputa: mp3 (matatū), wav, flac, ogg
speed float Kāore Ka whakarea te tere kōrero. Papatono: 1.0. Rārangi: 0.5 ki 2.0
language string Kāore Ko te waehere reo (hei tauira, en, es). Ka kitea-māori mēnā ka waihotia.
stream boolean Kāore Whakahaere i te urupare rerenga. Tūturu: whakahaere

Ka tono tauira

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

Ka urupare

Ka whakahokia te pūkete oro hei raraunga ā-rua me te taitapa tika Content-Type ( oro/mpeg, oro/wav, ērā atu mea).

Ko ngā pūmatua urupare
Content-Type: audio/mpeg
Content-Length: 48256
X-Credits-Used: 2
X-Credits-Remaining: 498

Ka kōrerorerotia te kuputuhi

POST /v1/stt/

Ka whakawhiti reo ki te kupu. E tautoko ana i ngā reo 99 me te kitenga aunoa.

Ka tono te tinana (multipart/form-data)

ParameterKāhuaE hiahiatia anaWhakamāramatanga
file file He Ko te pūkete oro (MP3, WAV, FLAC, OGG, M4A, MP4, WebM). Tūtohu 100MB.
model string Kāore Tauira STT: whisper (matatū), faster-whisper, sensevoice
language string Kāore Ko te waehere reo. auto mō te kitenga aunoa (whakahaere).
timestamps boolean Kāore Kei roto ko ngā tohu wā o te taumata-wā. Tūturu: pūnaha
diarize boolean Kāore Mā te whakahohe kaikōrero i te kaikōrero. Tūturu: whakahē

Ka urupare

Ka urupare a 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"
    }
  ]
}

Ko te tāruatanga reo

POST /v1/tts/clone/

Ka whakaputaina te kōrero i roto i tētahi reo tārua. Whakahauhau i tētahi oro tohutoro me te kupu.

Ka tono te tinana (multipart/form-data)

ParameterKāhuaE hiahiatia anaWhakamāramatanga
reference_audio file He Ko te oro oro tohutoro (10-30 sekon i whakaritea). 20MB te nui rawa.
text string He Ka kōrerotia te kupu i roto i te reo tārua.
model string Kāore Kāhua tārua: chatterbox (matatū), cosyvoice2, gpt-sovits
format string Kāore Hanganga huaputa: mp3 (matatū), wav, flac
language string Kāore Ko te waehere reo ūnga. Me tautokona e te tauira i kōwhiria.

Ka urupare

Ka hoki te pūkete oro hei raraunga ā-rua, pērā ki te wāhi mutunga TTS.

Kaitautoko reo

POST /v1/voice-convert/

Ka tahuri te oro hei oro pēnei i tētahi atu reo. Whakahauhau i te oro pūtake me te kōwhiri i tētahi reo ūnga.

Ka tono te tinana (multipart/form-data)

ParameterKāhuaE hiahiatia anaWhakamāramatanga
file file He Ko te pūtake o te pūkete oro (MP3, WAV, FLAC). Tūtohu 50MB.
target_voice string He Ko te tuakiri reo ūnga hei tahuri ki (ka whakamahia te /v1/voices/ hei whakarārangi i ngā reo e wātea ana)
model string Kāore Tauira tahuri reo: openvoice (matatū), knn-vc
format string Kāore Hanganga huaputa: wav (matatū), mp3, flac

Ka tono tauira

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

Ka urupare

Ka hoki te faila oro i tahuri hei raraunga ā-rua.

Whakamāoritanga kōrero

POST /v1/speech-translate/

Ka whakamāori i te oro i kōrerotia mai i tētahi reo ki tētahi atu. Ka whakakotahi i te kōrero ki te kupu, te whakamāoritanga, me te kupu-ki-te-kōrero i roto i tētahi kīanga kotahi.

Ka tono te tinana (multipart/form-data)

ParameterKāhuaE hiahiatia anaWhakamāramatanga
file file He Ko te pūtake o te pūkete oro i roto i te reo taketake. 100MB te nui rawa.
target_language string He Ko te waehere reo ūnga (hei tauira, es, fr, de, ja)
voice string Kāore Ko te reo mō te huaputa whakamāoritia. Ka tīpakotia mēnā ka waihotia.
preserve_voice boolean Kāore Ka ngana ki te pupuri i te kaikōrero taketake

Ka urupare

Ka urupare a 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
}

Whakawhitiwhiti ki te kōrero

POST /v1/speech-to-speech/

Ka whakarerekē te kāhua kōrero, te āhuahira, te whakarato rānei i te wā e pupuri ana i ngā ihirangi. Ka whai painga mō te whakarerekētanga o te tono, te whakatere, me te whakamāramatanga.

Ka tono te tinana (multipart/form-data)

ParameterKāhuaE hiahiatia anaWhakamāramatanga
file file He Ko te pūtake o te pūkete oro. Te nui rawa 50MB.
voice string He Ko te tuakiri reo ūnga mō te kōrero huaputa
model string Kāore Tauira: openvoice (matatū), chatterbox
emotion string Kāore Āhuatanga whāinga: kore, hauhau, āhuatanga, āhuatanga, āhuatanga, āhuatanga
speed float Kāore Ka whakaritea te tere. Papatono: 1.0. Rārangi: 0.5 ki 2.0

Ka urupare

Ka whakahokia te pūranga oro hei raraunga ā-rua.

Huakaʻi oro

Ko ngā wāhi mutunga o te tukanga oro mō te whakarei ake, te tango i te reo, te whakawehenga rākau, me ētahi atu.

POST /v1/audio/enhance/

Mā te whakarei ake i te āhuatanga oro: te whakarerekētanga, te whakarei ake i te mārama, te whakamāramatanga tino pai.

file fileKo te faila oro e whakarei ake ai
denoise booleanWhakahaere i te whakakoretanga (whakahaere: pono)
enhance_clarity booleanWhakarei ake i te mārama o te kōrero (whakarere: pono)
super_resolution booleanMā te whakapiki i te āhuatanga oro (whakahaere: hē)
strength integer1-3 (māmā, waenganui, kaha). Papatono: 2
POST /v1/audio/separate/

Mā te wehe i ngā pūoro mai i ngā utauta pūoro (hoatu pūoro), ka wehe rānei ki ngā rākau.

file fileKo te pūkete oro e wehe ana
model stringdemucs (Papatono) rānei spleeter
stems integerTe tau o ngā rākau: 2, 4, 5, 6 rānei (whakahitu: 2)
format stringHanganga huaputa: wav, mp3, flac
POST /v1/audio/dereverb/

Ka tangohia te whakairo me te whakairo mai i ngā pūkete oro.

file fileKo te faila oro e mahia ana
type stringecho or reverb (default: both)
intensity integer1-5 (default: 3)
POST /v1/audio/analyze/ Waihoki

Ka tātari i te oro hei kite i te kī, te BPM, me te tohu wā.

file fileKo te pūkete oro hei tātari
Ka urupare
{
  "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/ Waihoki

Ka tahuri te oro i waenganui i ngā hanga.

file fileKo te faila oro e tahuri ana
format stringHanganga ūnga: mp3, wav, flac, ogg, m4a, aac
bitrate integerKo te bitrate huaputa i roto i ngā kbps: 64, 128, 192, 256, 320
sample_rate integerTe mokatere tauira: 22050, 44100, 48000
channels stringmono rānei stereo

Pāpāho reo

POST /v1/voice-chat/

Ka tukuna te oro, te kupu rānei me te whiwhi whakautu AI me te kōrero i whakakotahitia.

Ka tono te tinana (multipart/form-data rānei JSON)

ParameterKāhuaE hiahiatia anaWhakamāramatanga
audio file Kāore* Ka hiahiatia te tāuru oro (oro, tuhi rānei)
text string Kāore* Ka hiahiatia te tāuru kupu (audio, text rānei)
voice string Kāore Whakapānga mō te urupare AI. Papatono: af_bella
tts_model string Kāore Tauira TTS mō te urupare. Papatono: kokoro
system_prompt string Kāore Ka tono te pūnaha kāwanatanga mō te AI
conversation_id string Kāore Ka haere tonu tētahi kōrero tīariari

Ka urupare

Ka urupare a 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
}

Tautuhi ngā tauira

GET /v1/models/

Ka hoki tētahi rārangi o ngā tauira katoa e wātea ana me ō rātou kaha.

Ka urupare

Ka urupare a 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
    }
  ]
}

Ko nga oro o te rārangi

GET /v1/voices/

Ka whakahokia tētahi rārangi o ngā reo katoa e wātea ana, e tātaritia ana e te tauira, e te reo rānei.

Pānga uiui

ParameterKāhuaWhakamāramatanga
model string Tōrō e te tauira ID (hei tauira, kokoro)
language string Tōrō e te waehere reo (hei tauira, en)
gender string Tōrō e te ira tangata: tāne, whanaunga, kore

Ka urupare

Ka urupare a 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
}

Ko ngā tauira waehere

Waihoki ki te kōrero

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')}")

Ka kōrerorerotia te kuputuhi

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"])

Ko te tāruatanga reo

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)

Waihoki ki te kōrero

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();

Ka kōrerorerotia te kuputuhi

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);

Waihoki ki te kōrero

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

Ka kōrerorerotia te kuputuhi

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"

Ko te tāruatanga reo

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

Whakarei ake reo

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

Ko ngā waehere hapa

Ka hoki ngā hapa katoa ki tētahi urupare JSON me tētahi error te āpure.

Hanganga urupare hapa
{
  "error": {
    "code": "insufficient_credits",
    "message": "You do not have enough credits for this request.",
    "credits_required": 4,
    "credits_available": 2
  }
}
Kāwanatanga HTTPKo te waehere hapaWhakamāramatanga
400 bad_request Parametera tono tē tika. Tirohia te karere hapa mō ngā taipitopito.
401 unauthorized Kua ngaro, kāore rānei i tika te kī API.
402 insufficient_credits Kāore i tino nui ngā pūtea. Kei te hoko anō i te /price/.
403 forbidden Kāore te āheitanga API i te wātea ki tōna mahere.
404 not_found Kāore i kitea te tauira, te reo rānei.
413 file_too_large Kua hipa te rārangi rahinga o te faila whakarewa.
429 rate_limited He maha rawa ngā tono. Tirohia ngā pūmatua tepe.
500 internal_error He hapa server. Ka ngana anō ā muri ake nei.
503 model_loading E kawe ana te tauira. Ka whakamātau anō i roto i ētahi waeine.

Webhooks

Mō ngā taumahi roa (whakahaeretanga pūtake, TTS rōpū), ka taea e koe te hoatu tētahi tohuāhua webhook_url. Ina oti te taumahi, ka POST tātau i te hua ki tōtou URL.

Webhook Payload
{
  "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"
}
Ka wātea ngā hua o te Webhook mō te tāpiritanga mo te 24 wā i muri i te whakaotitanga. Whakamātau ki te tāpiritanga tere.

E whakaritea ana?

Ki te whiwhi i tōkou kī API me te tīmata ki te whakauru i te TTS.ai ki roto i ōna taupānga.