File size: 2,484 Bytes
01e655b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d5b3cd8
01e655b
 
 
 
 
 
 
 
 
 
d5b3cd8
 
 
 
 
 
01e655b
 
 
 
 
 
 
 
d5b3cd8
 
01e655b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
from fastapi import HTTPException, Body
from fastapi.responses import StreamingResponse

import io
from pydantic import BaseModel
from fastapi.responses import FileResponse


from modules.normalization import text_normalize
from modules.ssml import parse_ssml
from modules.SynthesizeSegments import (
    SynthesizeSegments,
    synthesize_segment,
    combine_audio_segments,
)


from modules.api import utils as api_utils

from modules.api.Api import APIManager


class SSMLRequest(BaseModel):
    ssml: str
    format: str = "mp3"
    batch_size: int = 4


async def synthesize_ssml(
    request: SSMLRequest = Body(
        ..., description="JSON body with SSML string and format"
    )
):
    try:
        ssml = request.ssml
        format = request.format
        batch_size = request.batch_size

        if batch_size < 1:
            raise HTTPException(
                status_code=400, detail="Batch size must be greater than 0."
            )

        if not ssml:
            raise HTTPException(status_code=400, detail="SSML content is required.")

        segments = parse_ssml(ssml)
        for seg in segments:
            seg["text"] = text_normalize(seg["text"], is_end=True)

        if batch_size != 1:
            synthesize = SynthesizeSegments(batch_size)
            audio_segments = synthesize.synthesize_segments(segments)
            combined_audio = combine_audio_segments(audio_segments)
            buffer = io.BytesIO()
            combined_audio.export(buffer, format="wav")
            buffer.seek(0)
            if format == "mp3":
                buffer = api_utils.wav_to_mp3(buffer)
            return StreamingResponse(buffer, media_type=f"audio/{format}")
        else:

            def audio_streamer():
                for segment in segments:
                    audio_segment = synthesize_segment(segment=segment)
                    buffer = io.BytesIO()
                    audio_segment.export(buffer, format="wav")
                    buffer.seek(0)
                    if format == "mp3":
                        buffer = api_utils.wav_to_mp3(buffer)
                    yield buffer.read()

            return StreamingResponse(audio_streamer(), media_type=f"audio/{format}")

    except Exception as e:
        import logging

        logging.exception(e)
        raise HTTPException(status_code=500, detail=str(e))


def setup(api_manager: APIManager):
    api_manager.post("/v1/ssml", response_class=FileResponse)(synthesize_ssml)