File size: 9,617 Bytes
447ebeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
# What is this?
## unit tests for openai tts endpoint

import asyncio
import os
import random
import sys
import time
import traceback
import uuid

from dotenv import load_dotenv

load_dotenv()
import os

sys.path.insert(
    0, os.path.abspath("../..")
)  # Adds the parent directory to the system path
from pathlib import Path
from unittest.mock import AsyncMock, MagicMock, patch

import openai
import pytest

import litellm


@pytest.mark.parametrize(
    "sync_mode",
    [True, False],
)
@pytest.mark.parametrize(
    "model, api_key, api_base",
    [
        (
            "azure/azure-tts",
            os.getenv("AZURE_SWEDEN_API_KEY"),
            os.getenv("AZURE_SWEDEN_API_BASE"),
        ),
        ("openai/tts-1", os.getenv("OPENAI_API_KEY"), None),
    ],
)  # ,
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_audio_speech_litellm(sync_mode, model, api_base, api_key):
    speech_file_path = Path(__file__).parent / "speech.mp3"

    if sync_mode:
        response = litellm.speech(
            model=model,
            voice="alloy",
            input="the quick brown fox jumped over the lazy dogs",
            api_base=api_base,
            api_key=api_key,
            organization=None,
            project=None,
            max_retries=1,
            timeout=600,
            client=None,
            optional_params={},
        )

        from litellm.types.llms.openai import HttpxBinaryResponseContent

        assert isinstance(response, HttpxBinaryResponseContent)
    else:
        response = await litellm.aspeech(
            model=model,
            voice="alloy",
            input="the quick brown fox jumped over the lazy dogs",
            api_base=api_base,
            api_key=api_key,
            organization=None,
            project=None,
            max_retries=1,
            timeout=600,
            client=None,
            optional_params={},
        )

        from litellm.llms.openai.openai import HttpxBinaryResponseContent

        assert isinstance(response, HttpxBinaryResponseContent)


@pytest.mark.parametrize(
    "sync_mode",
    [False, True],
)
@pytest.mark.skip(reason="local only test - we run testing using MockRequests below")
@pytest.mark.asyncio
@pytest.mark.flaky(retries=3, delay=1)
async def test_audio_speech_litellm_vertex(sync_mode):
    litellm.set_verbose = True
    speech_file_path = Path(__file__).parent / "speech_vertex.mp3"
    model = "vertex_ai/test"
    if sync_mode:
        response = litellm.speech(
            model="vertex_ai/test",
            input="hello what llm guardrail do you have",
        )

        response.stream_to_file(speech_file_path)

    else:
        response = await litellm.aspeech(
            model="vertex_ai/",
            input="async hello what llm guardrail do you have",
        )

        from types import SimpleNamespace

        from litellm.llms.openai.openai import HttpxBinaryResponseContent

        response.stream_to_file(speech_file_path)


@pytest.mark.flaky(retries=6, delay=2)
@pytest.mark.asyncio
async def test_speech_litellm_vertex_async():
    # Mock the response
    mock_response = AsyncMock()

    def return_val():
        return {
            "audioContent": "dGVzdCByZXNwb25zZQ==",
        }

    mock_response.json = return_val
    mock_response.status_code = 200

    # Set up the mock for asynchronous calls
    with patch(
        "litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post",
        new_callable=AsyncMock,
    ) as mock_async_post:
        mock_async_post.return_value = mock_response
        model = "vertex_ai/test"

        try:
            response = await litellm.aspeech(
                model=model,
                input="async hello what llm guardrail do you have",
            )
        except litellm.APIConnectionError as e:
            if "Your default credentials were not found" in str(e):
                pytest.skip("skipping test, credentials not found")

        # Assert asynchronous call
        mock_async_post.assert_called_once()
        _, kwargs = mock_async_post.call_args
        print("call args", kwargs)

        assert kwargs["url"] == "https://texttospeech.googleapis.com/v1/text:synthesize"

        assert "x-goog-user-project" in kwargs["headers"]
        assert kwargs["headers"]["Authorization"] is not None

        assert kwargs["json"] == {
            "input": {"text": "async hello what llm guardrail do you have"},
            "voice": {"languageCode": "en-US", "name": "en-US-Studio-O"},
            "audioConfig": {"audioEncoding": "LINEAR16", "speakingRate": "1"},
        }


@pytest.mark.asyncio
async def test_speech_litellm_vertex_async_with_voice():
    # Mock the response
    mock_response = AsyncMock()

    def return_val():
        return {
            "audioContent": "dGVzdCByZXNwb25zZQ==",
        }

    mock_response.json = return_val
    mock_response.status_code = 200

    # Set up the mock for asynchronous calls
    with patch(
        "litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post",
        new_callable=AsyncMock,
    ) as mock_async_post:
        mock_async_post.return_value = mock_response
        model = "vertex_ai/test"

        try:
            response = await litellm.aspeech(
                model=model,
                input="async hello what llm guardrail do you have",
                voice={
                    "languageCode": "en-UK",
                    "name": "en-UK-Studio-O",
                },
                audioConfig={
                    "audioEncoding": "LINEAR22",
                    "speakingRate": "10",
                },
            )
        except litellm.APIConnectionError as e:
            if "Your default credentials were not found" in str(e):
                pytest.skip("skipping test, credentials not found")

        # Assert asynchronous call
        mock_async_post.assert_called_once()
        _, kwargs = mock_async_post.call_args
        print("call args", kwargs)

        assert kwargs["url"] == "https://texttospeech.googleapis.com/v1/text:synthesize"

        assert "x-goog-user-project" in kwargs["headers"]
        assert kwargs["headers"]["Authorization"] is not None

        assert kwargs["json"] == {
            "input": {"text": "async hello what llm guardrail do you have"},
            "voice": {"languageCode": "en-UK", "name": "en-UK-Studio-O"},
            "audioConfig": {"audioEncoding": "LINEAR22", "speakingRate": "10"},
        }


@pytest.mark.asyncio
async def test_speech_litellm_vertex_async_with_voice_ssml():
    # Mock the response
    mock_response = AsyncMock()

    def return_val():
        return {
            "audioContent": "dGVzdCByZXNwb25zZQ==",
        }

    mock_response.json = return_val
    mock_response.status_code = 200

    ssml = """
    <speak>
        <p>Hello, world!</p>
        <p>This is a test of the <break strength="medium" /> text-to-speech API.</p>
    </speak>
    """

    # Set up the mock for asynchronous calls
    with patch(
        "litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post",
        new_callable=AsyncMock,
    ) as mock_async_post:
        mock_async_post.return_value = mock_response
        model = "vertex_ai/test"

        try:
            response = await litellm.aspeech(
                input=ssml,
                model=model,
                voice={
                    "languageCode": "en-UK",
                    "name": "en-UK-Studio-O",
                },
                audioConfig={
                    "audioEncoding": "LINEAR22",
                    "speakingRate": "10",
                },
            )
        except litellm.APIConnectionError as e:
            if "Your default credentials were not found" in str(e):
                pytest.skip("skipping test, credentials not found")

        # Assert asynchronous call
        mock_async_post.assert_called_once()
        _, kwargs = mock_async_post.call_args
        print("call args", kwargs)

        assert kwargs["url"] == "https://texttospeech.googleapis.com/v1/text:synthesize"

        assert "x-goog-user-project" in kwargs["headers"]
        assert kwargs["headers"]["Authorization"] is not None

        assert kwargs["json"] == {
            "input": {"ssml": ssml},
            "voice": {"languageCode": "en-UK", "name": "en-UK-Studio-O"},
            "audioConfig": {"audioEncoding": "LINEAR22", "speakingRate": "10"},
        }


@pytest.mark.skip(reason="causes openai rate limit errors")
def test_audio_speech_cost_calc():
    from litellm.integrations.custom_logger import CustomLogger

    model = "azure/azure-tts"
    api_base = os.getenv("AZURE_SWEDEN_API_BASE")
    api_key = os.getenv("AZURE_SWEDEN_API_KEY")

    custom_logger = CustomLogger()
    litellm.set_verbose = True

    with patch.object(custom_logger, "log_success_event") as mock_cost_calc:
        litellm.callbacks = [custom_logger]
        litellm.speech(
            model=model,
            voice="alloy",
            input="the quick brown fox jumped over the lazy dogs",
            api_base=api_base,
            api_key=api_key,
            base_model="azure/tts-1",
        )

        time.sleep(1)

        mock_cost_calc.assert_called_once()

        print(
            f"mock_cost_calc.call_args: {mock_cost_calc.call_args.kwargs['kwargs'].keys()}"
        )
        standard_logging_payload = mock_cost_calc.call_args.kwargs["kwargs"][
            "standard_logging_object"
        ]
        print(f"standard_logging_payload: {standard_logging_payload}")
        assert standard_logging_payload["response_cost"] > 0