File size: 3,211 Bytes
377c6b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
30c81b8
 
377c6b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
# app/main.py

import json
import httpx
from fastapi import FastAPI, HTTPException
from fastapi.responses import StreamingResponse, Response
from pydantic import BaseModel, Field

CONFIG_PATH = "app/config.json"


def load_config() -> dict:
    with open(CONFIG_PATH, "r") as f:
        return json.load(f)


config = load_config()

EL_API_KEY = config["elevenlabs"]["api_key"]
VOICE_ID = config["elevenlabs"]["voice_id"]
MODEL_ID = config["elevenlabs"]["model_id"]

ELEVENLABS_STREAM_URL = (
    f"https://api.elevenlabs.io/v1/text-to-speech/{VOICE_ID}/stream"
)

HEADERS = {
    "xi-api-key": EL_API_KEY,
    "Content-Type": "application/json",
    "Accept": "audio/mpeg",
}

app = FastAPI(
    title="Production TTS Service",
    version="1.0.2",
    docs_url="/docs",
    redoc_url="/redoc",
)




class TTSRequest(BaseModel):
    text: str = Field(..., min_length=1, max_length=5000)
    stability: float = Field(0.5, ge=0.0, le=1.0)
    similarity_boost: float = Field(0.5, ge=0.0, le=1.0)


@app.get("/health")
async def health():
    return {"status": "ok"}



@app.post("/tts")
async def text_to_speech(payload: TTSRequest):
    body = {
        "text": payload.text,
        "model_id": MODEL_ID,
        "voice_settings": {
            "stability": payload.stability,
            "similarity_boost": payload.similarity_boost,
        },
    }

    async def audio_stream():
        async with httpx.AsyncClient(timeout=None) as client:
            async with client.stream(
                method="POST",
                url=ELEVENLABS_STREAM_URL,
                headers=HEADERS,
                json=body,
            ) as response:

                if response.status_code != 200:
                    error = await response.aread()
                    raise HTTPException(
                        status_code=502,
                        detail=error.decode(),
                    )

                async for chunk in response.aiter_bytes():
                    yield chunk

    return StreamingResponse(
        audio_stream(),
        media_type="audio/mpeg",
        headers={
            "Content-Disposition": "inline; filename=tts.mp3",
        },
    )



@app.post("/tts/buffered")
async def text_to_speech_buffered(payload: TTSRequest):
    body = {
        "text": payload.text,
        "model_id": MODEL_ID,
        "voice_settings": {
            "stability": payload.stability,
            "similarity_boost": payload.similarity_boost,
        },
    }

    async with httpx.AsyncClient(timeout=30.0) as client:
        response = await client.post(
            ELEVENLABS_STREAM_URL,
            headers=HEADERS,
            json=body,
        )

    if response.status_code != 200:
        raise HTTPException(
            status_code=502,
            detail=response.text,
        )

    if not response.content:
        raise HTTPException(
            status_code=500,
            detail="Received empty audio buffer",
        )

    return Response(
        content=response.content,
        media_type="audio/mpeg",
        headers={
            "Content-Disposition": "attachment; filename=tts.mp3",
            "Content-Length": str(len(response.content)),
        },
    )