apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-07-25 12:01:04 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add custom sarvam tts voice

Browse source
This commit is contained in:
Sabiha Khan 2026-06-17 17:18:41 +05:30
parent a2d9ed24ed
commit 7c919264f9
4 changed files with 61 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

1
api/services/configuration/registry.py
View file

@ -990,6 +990,7 @@ class SarvamTTSConfiguration(BaseTTSConfiguration):
description="Sarvam voice name; must match the selected model's voice list.",
json_schema_extra={
"examples": SARVAM_V2_VOICES,
"allow_custom_input": True,
"model_options": {
"bulbul:v2": SARVAM_V2_VOICES,
"bulbul:v3": SARVAM_V3_VOICES,

2
api/services/pipecat/service_factory.py
View file

@ -534,7 +534,7 @@ def create_tts_service(
language = getattr(user_config.tts, "language", None)
pipecat_language = language_mapping.get(language, Language.HI)
voice = getattr(user_config.tts, "voice", None) or "anushka"
voice = (getattr(user_config.tts, "voice", None) or "anushka").strip().lower()
speed = getattr(user_config.tts, "speed", None)
settings_kwargs = {
"model": user_config.tts.model,

32
api/tests/test_sarvam_service_factory.py
View file

@ -126,6 +126,15 @@ class TestSarvamTTSServiceFactory:
assert config.language == "hi-IN"
assert config.speed == 1.0
def test_sarvam_tts_voice_schema_allows_custom_model_specific_options(self):
voice_schema = SarvamTTSConfiguration.model_json_schema()["properties"][
"voice"
]
assert voice_schema["allow_custom_input"] is True
assert "bulbul:v2" in voice_schema["model_options"]
assert "bulbul:v3" in voice_schema["model_options"]
def test_create_sarvam_tts_service_maps_speed_to_pace(self):
user_config = SimpleNamespace(
tts=SimpleNamespace(
@ -152,3 +161,26 @@ class TestSarvamTTSServiceFactory:
assert kwargs["settings"].voice == "anushka"
assert kwargs["settings"].language == Language.HI
assert kwargs["settings"].pace == 1.25
def test_create_sarvam_tts_service_normalizes_custom_voice_id(self):
user_config = SimpleNamespace(
tts=SimpleNamespace(
provider=ServiceProviders.SARVAM.value,
api_key="test-key",
model="bulbul:v2",
voice=" Rehan ",
language="hi-IN",
speed=1.0,
)
)
audio_config = AudioConfig(
transport_in_sample_rate=16000, transport_out_sample_rate=16000
)
with patch(
"api.services.pipecat.service_factory.SarvamTTSService"
) as mock_service:
create_tts_service(user_config, audio_config)
kwargs = mock_service.call_args.kwargs
assert kwargs["settings"].voice == "rehan"