public-mirrors/Kokoro-FastAPI
1
0
Fork 0
mirror of https://github.com/remsky/Kokoro-FastAPI.git synced 2025-08-05 16:48:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Replaced default voice with af_heart as af doesn't exist

Browse source
This commit is contained in:
Fireblade 2025-02-15 12:36:36 -05:00
parent 8c457c3292
commit 4802128943
7 changed files with 11 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
api/src/structures/schemas.py
View file

@ -54,7 +54,7 @@ class OpenAISpeechRequest(BaseModel):
) )
input: str = Field(..., description="The text to generate audio for") input: str = Field(..., description="The text to generate audio for")
voice: str = Field( voice: str = Field(
default="af", default="af_heart",
description="The voice to use for generation. Can be a base voice or a combined voice name.", description="The voice to use for generation. Can be a base voice or a combined voice name.",
) )
response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] = Field( response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] = Field(
@ -98,7 +98,7 @@ class CaptionedSpeechRequest(BaseModel):
) )
input: str = Field(..., description="The text to generate audio for") input: str = Field(..., description="The text to generate audio for")
voice: str = Field( voice: str = Field(
default="af", default="af_heart",
description="The voice to use for generation. Can be a base voice or a combined voice name.", description="The voice to use for generation. Can be a base voice or a combined voice name.",
) )
response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] = Field( response_format: Literal["mp3", "opus", "aac", "flac", "wav", "pcm"] = Field(

2
examples/assorted_checks/benchmarks/benchmark_first_token.py
View file

@ -34,7 +34,7 @@ def measure_first_token(
json={ json={
"model": "kokoro", "model": "kokoro",
"input": text, "input": text,
"voice": "af", "voice": "af_heart",
"response_format": "wav", "response_format": "wav",
"stream": False, "stream": False,
}, },

4
examples/assorted_checks/benchmarks/benchmark_first_token_stream_unified.py
View file

@ -34,7 +34,7 @@ def measure_first_token_requests(
json={ json={
"model": "kokoro", "model": "kokoro",
"input": text, "input": text,
"voice": "af", "voice": "af_heart",
"response_format": "pcm", "response_format": "pcm",
"stream": True, "stream": True,
}, },
@ -123,7 +123,7 @@ def measure_first_token_openai(
# Make streaming request using OpenAI client # Make streaming request using OpenAI client
with OPENAI_CLIENT.audio.speech.with_streaming_response.create( with OPENAI_CLIENT.audio.speech.with_streaming_response.create(
model="kokoro", model="kokoro",
voice="af", voice="af_heart",
response_format="pcm", response_format="pcm",
input=text, input=text,
) as response: ) as response:

4
examples/assorted_checks/benchmarks/lib/shared_benchmark_utils.py
View file

@ -56,7 +56,7 @@ def make_tts_request(
json={ json={
"model": "kokoro", "model": "kokoro",
"input": text, "input": text,
"voice": "af", "voice": "af_heart",
"response_format": "wav", "response_format": "wav",
"stream": True, "stream": True,
}, },
@ -77,7 +77,7 @@ def make_tts_request(
json={ json={
"model": "kokoro", "model": "kokoro",
"input": text, "input": text,
"voice": "af", "voice": "af_heart",
"response_format": "wav", "response_format": "wav",
"stream": False, "stream": False,
}, },

2
examples/assorted_checks/test_formats/test_audio_formats.py
View file

@ -246,7 +246,7 @@ def main():
output_dir.mkdir(exist_ok=True, parents=True) output_dir.mkdir(exist_ok=True, parents=True)
# First generate audio in each format using the API # First generate audio in each format using the API
voice = "af" # Using default voice voice = "af_heart" # Using default voice
formats = ["wav", "mp3", "opus", "flac", "pcm"] formats = ["wav", "mp3", "opus", "flac", "pcm"]
stats = [] stats = []

4
examples/assorted_checks/test_openai/test_openai_tts.py
View file

@ -23,7 +23,7 @@ def test_format(
try: try:
response = client.audio.speech.create( response = client.audio.speech.create(
model="tts-1", voice="af", input=text, response_format=format model="tts-1", voice="af_heart", input=text, response_format=format
) )
print("Got response, saving to file...") print("Got response, saving to file...")
@ -43,7 +43,7 @@ def test_speed(speed: float):
try: try:
response = client.audio.speech.create( response = client.audio.speech.create(
model="tts-1", model="tts-1",
voice="af", voice="af_heart",
input="The quick brown fox jumped over the lazy dog.", input="The quick brown fox jumped over the lazy dog.",
response_format="wav", response_format="wav",
speed=speed, speed=speed,

2
ui/depr_tests/conftest.py
View file

@ -16,7 +16,7 @@ async def mock_model_manager():
async def mock_voice_manager(): async def mock_voice_manager():
"""Mock voice manager for UI tests""" """Mock voice manager for UI tests"""
manager = AsyncMock() manager = AsyncMock()
manager.list_voices = AsyncMock(return_value=["af", "bm_lewis", "af_sarah"]) manager.list_voices = AsyncMock(return_value=["af_heart", "bm_lewis", "af_sarah"])
return manager return manager