apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-07-04 10:52:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

feat: add Inworld TTS provider support (#420)

Browse source 
* Add Inworld TTS provider integration

* chore: move from HTTP Service to Websocket Service

---------

Co-authored-by: Abhishek Kumar <abhishek@a6k.me>
This commit is contained in:
Manasseh 2026-06-19 09:53:27 +02:00 • committed by GitHub
parent 00a0de8a62
commit fc37d5058f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 160 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

54
api/services/configuration/registry.py
View file

@ -61,6 +61,7 @@ class ServiceProviders(str, Enum):
DEEPGRAM = "deepgram"
GROQ = "groq"
OPENROUTER = "openrouter"
INWORLD = "inworld"
CARTESIA = "cartesia"
# NEUPHONIC = "neuphonic"
ELEVENLABS = "elevenlabs"
@ -94,6 +95,7 @@ class BaseServiceConfiguration(BaseModel):
ServiceProviders.DEEPGRAM,
ServiceProviders.GROQ,
ServiceProviders.OPENROUTER,
ServiceProviders.INWORLD,
ServiceProviders.ELEVENLABS,
ServiceProviders.GOOGLE,
ServiceProviders.AZURE,
@ -249,6 +251,14 @@ GOOGLE_VERTEX_REALTIME_PROVIDER_MODEL_CONFIG = provider_model_config(
DEEPGRAM_PROVIDER_MODEL_CONFIG = provider_model_config("Deepgram")
ELEVENLABS_PROVIDER_MODEL_CONFIG = provider_model_config("ElevenLabs")
CARTESIA_PROVIDER_MODEL_CONFIG = provider_model_config("Cartesia")
INWORLD_PROVIDER_MODEL_CONFIG = provider_model_config(
"Inworld",
description=(
"Inworld AI streaming text-to-speech with built-in and cloned voices. "
"Defaults to the Ashley system voice on inworld-tts-2."
),
provider_docs_url="https://docs.inworld.ai/tts/tts",
)
SARVAM_PROVIDER_MODEL_CONFIG = provider_model_config("Sarvam")
CAMB_PROVIDER_MODEL_CONFIG = provider_model_config("Camb.ai")
RIME_PROVIDER_MODEL_CONFIG = provider_model_config("Rime")
@ -957,6 +967,9 @@ class DograhTTSService(BaseTTSConfiguration):
CARTESIA_TTS_MODELS = ["sonic-3.5", "sonic-3"]
INWORLD_TTS_MODELS = ["inworld-tts-2"]
INWORLD_TTS_VOICES = ["Ashley"]
INWORLD_TTS_LANGUAGES = ["en-US"]
@register_tts
@ -986,6 +999,46 @@ class CartesiaTTSConfiguration(BaseTTSConfiguration):
)
@register_tts
class InworldTTSConfiguration(BaseTTSConfiguration):
model_config = INWORLD_PROVIDER_MODEL_CONFIG
provider: Literal[ServiceProviders.INWORLD] = ServiceProviders.INWORLD
model: str = Field(
default="inworld-tts-2",
description="Inworld TTS model.",
json_schema_extra={"examples": INWORLD_TTS_MODELS, "allow_custom_input": True},
)
voice: str = Field(
default="Ashley",
description=(
"Inworld voice ID. Use Ashley for the default warm English voice, "
"or a workspace voice ID for a cloned/custom voice."
),
json_schema_extra={"examples": INWORLD_TTS_VOICES, "allow_custom_input": True},
)
language: str = Field(
default="en-US",
description="BCP-47 language code for synthesis.",
json_schema_extra={
"examples": INWORLD_TTS_LANGUAGES,
"allow_custom_input": True,
},
)
speed: float = Field(
default=1.0,
ge=0.25,
le=4.0,
description="Speech speed multiplier.",
)
delivery_mode: Literal["STABLE", "BALANCED", "CREATIVE"] = Field(
default="BALANCED",
description=(
"Controls stability versus expressiveness for inworld-tts-2 "
"(STABLE, BALANCED, or CREATIVE)."
),
)
@register_tts
class SarvamTTSConfiguration(BaseTTSConfiguration):
model_config = SARVAM_PROVIDER_MODEL_CONFIG
@ -1228,6 +1281,7 @@ TTSConfig = Annotated[
OpenAITTSService,
ElevenlabsTTSConfiguration,
CartesiaTTSConfiguration,
InworldTTSConfiguration,
DograhTTSService,
SarvamTTSConfiguration,
CambTTSConfiguration,