transition Hathora service to use the unified API and apply PR feedback

add Hathora to root files

Hathora run linter

added hathora changelog

README.md

@@ -73,9 +73,9 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
 
 | Category            | Services                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                            |
+| Speech-to-Text      | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [Hathora](https://docs.pipecat.ai/server/services/stt/hathora), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper)                                                                                                                                                                                                                                                            |
 | LLMs                | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together)                                                                                                                                                                                                                                                                                              |
-| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
+| Text-to-Speech      | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Camb AI](https://docs.pipecat.ai/server/services/tts/camb), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hathora](https://docs.pipecat.ai/server/services/tts/hathora), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
 | Speech-to-Speech    | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox),                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 | Transport           | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                |
 | Serializers         | [Exotel](https://docs.pipecat.ai/server/utilities/serializers/exotel), [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx), [Vonage](https://docs.pipecat.ai/server/utilities/serializers/vonage)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |

changelog/3169.added.md

@@ -0,0 +1 @@
+- Added Hathora service to support Hathora-hosted TTS and STT models (only non-streaming)

env.example

@@ -85,6 +85,9 @@ GROK_API_KEY=...
 # Groq
 GROQ_API_KEY=...
 
+# Hathora
+HATHORA_API_KEY=...
+
 # Heygen
 HEYGEN_API_KEY=...
 HEYGEN_LIVE_AVATAR_API_KEY=...

examples/foundational/07ag-interruptible-hathora.py

@@ -21,8 +21,8 @@ from pipecat.processors.aggregators.llm_context import LLMContext
 from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
 from pipecat.runner.types import RunnerArguments
 from pipecat.runner.utils import create_transport
-from pipecat.services.hathora.stt import ParakeetSTTService
+from pipecat.services.hathora.stt import HathoraSTTService
-from pipecat.services.hathora.tts import ChatterboxTTSService, KokoroTTSService
+from pipecat.services.hathora.tts import HathoraTTSService
 from pipecat.services.openai.llm import OpenAILLMService
 from pipecat.transports.base_transport import BaseTransport, TransportParams
 from pipecat.transports.daily.transport import DailyParams
@@ -38,13 +38,19 @@ transport_params = {
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
+    ),
+    "twilio": lambda: FastAPIWebsocketParams(
+        audio_in_enabled=True,
+        audio_out_enabled=True,
+        vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
     "webrtc": lambda: TransportParams(
         audio_in_enabled=True,
         audio_out_enabled=True,
         vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
-        turn_analyzer=LocalSmartTurnAnalyzerV3(),
+        turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
     ),
 }
 
@@ -52,24 +58,14 @@ transport_params = {
 async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
     logger.info(f"Starting bot")
 
-    # See https://models.hathora.dev/model/nvidia-parakeet-tdt-0.6b-v3
+    stt = HathoraSTTService(
-    stt = ParakeetTDTSTTService(
+        model="nvidia-parakeet-tdt-0.6b-v3",
-        base_url="https://app-1c7bebb9-6977-4101-9619-833b251b86d1.app.hathora.dev/v1/transcribe",
-        api_key=os.getenv("HATHORA_API_KEY")
     )
 
-    # See https://models.hathora.dev/model/hexgrad-kokoro-82m
+    tts = HathoraTTSService(
-    tts = KokoroTTSService(
+        model="hexgrad-kokoro-82m",
-        base_url="https://app-01312daf-6e53-4b9d-a4ad-13039f35adc4.app.hathora.dev/synthesize",
-        api_key=os.getenv("HATHORA_API_KEY"),
     )
 
-    # See https://models.hathora.dev/model/resemble-ai-chatterbox
-    # tts = ChatterboxTTSService(
-    #     base_url="https://app-efbc8fe2-df55-4f96-bbe3-74f6ea9d986b.app.hathora.dev/v1/generate",
-    #     api_key=os.getenv("HATHORA_API_KEY")
-    # )
-
     # See https://models.hathora.dev/model/qwen3-30b-a3b
     llm = OpenAILLMService(
         base_url="https://app-362f7ca1-6975-4e18-a605-ab202bf2c315.app.hathora.dev/v1",

src/pipecat/services/hathora/__init__.py

@@ -1,14 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import sys
-
-from pipecat.services import DeprecatedModuleProxy
-
-from .stt import *
-from .tts import *
-
-sys.modules[__name__] = DeprecatedModuleProxy(globals(), "hathora", "hathora.[stt,tts]")

src/pipecat/services/hathora/stt.py

@@ -6,102 +6,126 @@
 
 """[Hathora-hosted](https://models.hathora.dev) speech-to-text services."""
 
+import base64
 import os
-from typing import Optional
+from typing import AsyncGenerator, Optional
 
 import aiohttp
-from loguru import logger
 
 from pipecat.frames.frames import (
     ErrorFrame,
+    Frame,
     TranscriptionFrame,
 )
 from pipecat.services.stt_service import SegmentedSTTService
 from pipecat.transcriptions.language import Language
 from pipecat.utils.time import time_now_iso8601
+from pipecat.utils.tracing.service_decorators import traced_stt
 
-class ParakeetTDTSTTService(SegmentedSTTService):
+from .utils import ConfigOption
-    """Parakeet TDT is a multilingual automatic speech recognition model
-    with word-level timestamps.
 
-    This service uses the Hathora-hosted Parakeet model via the HTTP API.
 
-    [Documentation](https://models.hathora.dev/model/nvidia-parakeet-tdt-0.6b-v3)
+class HathoraSTTService(SegmentedSTTService):
+    """This service supports several different speech-to-text models hosted by Hathora.
+
+    [Documentation](https://models.hathora.dev)
     """
 
     def __init__(
         self,
         *,
-        base_url = None,
+        model: str,
-        api_key = None,
+        language: Optional[str] = None,
-        start_time: Optional[int] = None,
+        model_config: Optional[list[ConfigOption]] = None,
-        end_time: Optional[int] = None,
+        base_url: str = "https://api.models.hathora.dev/inference/v1/stt",
+        api_key: Optional[str] = None,
         **kwargs,
     ):
-        """Initialize the Hathora-hosted Parakeet STT service.
+        """Initialize the Hathora STT service.
 
         Args:
-            base_url: Base URL for the Hathora Parakeet STT API.
+            model: Model to use; find available models
+                [here](https://models.hathora.dev).
+            language: Language code (if supported by model).
+            model_config: Some models support additional config, refer to
+                [docs](https://models.hathora.dev) for each model to see
+                what is supported.
+            base_url: Base API URL for the Hathora STT service.
             api_key: API key for authentication with the Hathora service;
-                provisiion one [here](https://models.hathora.dev/tokens).
+                provision one [here](https://models.hathora.dev/tokens).
-            start_time: Start time in seconds for the time window.
+            **kwargs: Additional arguments passed to the parent class.
-            end_time: End time in seconds for the time window.
         """
         super().__init__(
             **kwargs,
         )
+        self._model = model
+        self._language = language
+        self._model_config = model_config
         self._base_url = base_url
-        self._api_key = api_key
+        self._api_key = api_key or os.getenv("HATHORA_API_KEY")
-        self._start_time = start_time
-        self._end_time = end_time
 
-    def can_generate_metrics(self) -> bool:
+    @traced_stt
-        return True
+    async def _handle_transcription(
+        self, transcript: str, is_final: bool, language: Optional[Language] = None
+    ):
+        """Handle a transcription result with tracing."""
+        pass
 
-    async def run_stt(self, audio: bytes):
+    @traced_stt
+    async def run_stt(self, audio: bytes) -> AsyncGenerator[Frame, None]:
+        """Run speech-to-text on the provided audio data.
+
+        Args:
+            audio: Raw audio bytes to transcribe.
+
+        Yields:
+            Frame: Frames containing transcription results (typically TextFrame).
+        """
         try:
             await self.start_processing_metrics()
             await self.start_ttfb_metrics()
 
             url = f"{self._base_url}"
 
-            url_query_params = []
+            payload = {
-            if self._start_time is not None:
+                "model": self._model,
-                url_query_params.append(f"start_time={self._start_time}")
+            }
-            if self._end_time is not None:
-                url_query_params.append(f"end_time={self._end_time}")
-            url_query_params.append(f"sample_rate={self.sample_rate}")
 
-            if len(url_query_params) > 0:
+            if self._language is not None:
-                url += "?" + "&".join(url_query_params)
+                payload["language"] = self._language
+            if self._model_config is not None:
+                payload["model_config"] = [
+                    {"name": option.name, "value": option.value} for option in self._model_config
+                ]
 
-            api_key = self._api_key or os.getenv("HATHORA_API_KEY")
+            base64_audio = base64.b64encode(audio).decode("utf-8")
-
+            payload["audio"] = base64_audio
-            form_data = aiohttp.FormData()
-            form_data.add_field("file", audio, filename="audio.wav", content_type="application/octet-stream")
 
             async with aiohttp.ClientSession() as session:
                 async with session.post(
                     url,
-                    headers={"Authorization": f"Bearer {api_key}"},
+                    headers={"Authorization": f"Bearer {self._api_key}"},
-                    data=form_data,
+                    json=payload,
                 ) as resp:
                     response = await resp.json()
 
             if response and "text" in response:
                 text = response["text"].strip()
                 if text:  # Only yield non-empty text
-                    await self.stop_ttfb_metrics()
+                    # Hathora's API currently doesn't return language info
-                    await self.stop_processing_metrics()
+                    # so we default to the requested language or "en"
-                    logger.debug(f"Transcription: [{text}]")
+                    response_language = self._language or "en"
+                    await self._handle_transcription(text, True, response_language)
                     yield TranscriptionFrame(
                         text,
                         self._user_id,
                         time_now_iso8601(),
-                        Language("en"), # TODO: the parakeet hathora API doesn't accept a language but says it's multilingual
+                        Language(response_language),
                         result=response,
                     )
 
+            await self.stop_ttfb_metrics()
+            await self.stop_processing_metrics()
+
         except Exception as e:
-            logger.error(f"Hathora error: {e}")
+            yield ErrorFrame(error=f"Unknown error occurred: {e}")
-            yield ErrorFrame(f"Hathora error: {str(e)}")

src/pipecat/services/hathora/tts.py

@@ -9,18 +9,22 @@
 import io
 import os
 import wave
-from typing import Optional, Tuple
+from typing import AsyncGenerator, Optional, Tuple
 
 import aiohttp
-from loguru import logger
 
 from pipecat.frames.frames import (
     ErrorFrame,
+    Frame,
     TTSAudioRawFrame,
     TTSStartedFrame,
     TTSStoppedFrame,
 )
 from pipecat.services.tts_service import TTSService
+from pipecat.utils.tracing.service_decorators import traced_tts
+
+from .utils import ConfigOption
+
 
 def _decode_audio_payload(
     audio_bytes: bytes,
@@ -29,7 +33,6 @@ def _decode_audio_payload(
     fallback_channels: int = 1,
 ) -> Tuple[bytes, int, int]:
     """Convert a WAV/PCM payload into raw PCM samples for TTSAudioRawFrame."""
-
     try:
         with wave.open(io.BytesIO(audio_bytes), "rb") as wav_reader:
             channels = wav_reader.getnchannels()
@@ -40,69 +43,82 @@ def _decode_audio_payload(
         # If the payload is already raw PCM, just pass it through.
         return audio_bytes, fallback_sample_rate, fallback_channels
 
-class KokoroTTSService(TTSService):
-    """Kokoro is an open-weight TTS model with 82 million parameters.
 
-    This service uses the Hathora-hosted Kokoro model via the HTTP API.
+class HathoraTTSService(TTSService):
+    """This service supports several different text-to-speech models hosted by Hathora.
 
-    [Documentation](https://models.hathora.dev/model/hexgrad-kokoro-82m)
+    [Documentation](https://models.hathora.dev)
     """
 
     def __init__(
         self,
         *,
-        base_url = None,
+        model: str,
-        api_key = None,
         voice: Optional[str] = None,
         speed: Optional[float] = None,
+        model_config: Optional[list[ConfigOption]] = None,
+        base_url: str = "https://api.models.hathora.dev/inference/v1/tts",
+        api_key: Optional[str] = None,
         **kwargs,
     ):
-        """Initialize the Hathora-hosted Kokoro TTS service.
+        """Initialize the Hathora TTS service.
 
         Args:
-            base_url: Base URL for the Hathora Kokoro TTS API, .
+            model: Model to use; find available models
+                [here](https://models.hathora.dev).
+            voice: Voice to use for synthesis (if supported by model).
+            speed: Speech speed multiplier (if supported by model).
+            model_config: Some models support additional config, refer to
+                [docs](https://models.hathora.dev) for each model to see
+                what is supported.
+            base_url: Base API URL for the Hathora TTS service.
             api_key: API key for authentication with the Hathora service;
-                provisiion one [here](https://models.hathora.dev/tokens).
+                provision one [here](https://models.hathora.dev/tokens).
-            voice: Voice to use for synthesis (see the
+            **kwargs: Additional arguments passed to the parent class.
-                [Hathora docs](https://models.hathora.dev/model/hexgrad-kokoro-82m)
-                for the default value; [list of voices](https://huggingface.co/hexgrad/Kokoro-82M/blob/main/VOICES.md)).
-            speed: Speech speed multiplier (0.5 = half speed, 2.0 = double speed, default: 1).
         """
         super().__init__(
             **kwargs,
         )
-        self._base_url = base_url
+        self._model = model
-        self._api_key = api_key
         self._voice = voice
         self._speed = speed
+        self._model_config = model_config
+        self._base_url = base_url
+        self._api_key = api_key or os.getenv("HATHORA_API_KEY")
 
-    def can_generate_metrics(self) -> bool:
+    @traced_tts
-        return True
+    async def run_tts(self, text: str) -> AsyncGenerator[Frame, None]:
+        """Run text-to-speech synthesis on the provided text.
 
-    async def run_tts(self, text: str):
+        Args:
+            text: The text to synthesize into speech.
+
+        Yields:
+            Frame: Audio frames containing the synthesized speech.
+        """
         try:
             await self.start_processing_metrics()
             await self.start_ttfb_metrics()
 
             url = f"{self._base_url}"
 
-            api_key = self._api_key or os.getenv("HATHORA_API_KEY")
+            payload = {"model": self._model, "text": text}
-
-            payload = {
-                "text": text
-            }
 
             if self._voice is not None:
                 payload["voice"] = self._voice
             if self._speed is not None:
                 payload["speed"] = self._speed
+            if self._model_config is not None:
+                payload["model_config"] = [
+                    {"name": option.name, "value": option.value} for option in self._model_config
+                ]
 
             yield TTSStartedFrame()
 
             async with aiohttp.ClientSession() as session:
                 async with session.post(
                     url,
-                    headers={"Authorization": f"Bearer {api_key}", "Accept": "application/octet-stream"},
+                    headers={"Authorization": f"Bearer {self._api_key}"},
                     json=payload,
                 ) as resp:
                     audio_data = await resp.read()
@@ -112,8 +128,6 @@ class KokoroTTSService(TTSService):
                 fallback_sample_rate=self.sample_rate or self._init_sample_rate or 24000,
             )
 
-            await self.stop_ttfb_metrics()
-
             frame = TTSAudioRawFrame(
                 audio=pcm_audio,
                 sample_rate=sample_rate,
@@ -123,107 +137,8 @@ class KokoroTTSService(TTSService):
             yield frame
 
         except Exception as e:
-            logger.error(f"Hathora error: {e}")
+            yield ErrorFrame(error=f"Unknown error occurred: {e}")
-            yield ErrorFrame(f"Hathora error: {str(e)}")
         finally:
             await self.stop_ttfb_metrics()
             await self.stop_processing_metrics()
             yield TTSStoppedFrame()
-
-class ChatterboxTTSService(TTSService):
-    """Chatterbox is a public text-to-speech model optimized for natural and expressive voice synthesis.
-
-    This service uses the Hathora-hosted Chatterbox model via the HTTP API.
-
-    [Documentation](https://models.hathora.dev/model/resemble-ai-chatterbox)
-    """
-
-    def __init__(
-        self,
-        *,
-        base_url = None,
-        api_key = None,
-        exaggeration: Optional[float] = None,
-        audio_prompt: Optional[bytes] = None,
-        cfg_weight: Optional[float] = None,
-        **kwargs,
-    ):
-        """Initialize the Hathora-hosted Chatterbox TTS service.
-
-        Args:
-            base_url: Base URL for the Hathora Chatterbox TTS API.
-            api_key: API key for authentication with the Hathora service;
-                provisiion one [here](https://models.hathora.dev/tokens).
-            exaggeration: Controls emotional intensity (default: 0.5).
-            audio_prompt: Reference audio file for voice cloning.
-            cfg_weight: Controls adherence to reference voice (default: 0.5).
-        """
-
-        super().__init__(
-            **kwargs,
-        )
-        self._base_url = base_url
-        self._api_key = api_key
-        self._exaggeration = exaggeration
-        self._audio_prompt = audio_prompt
-        self._cfg_weight = cfg_weight
-
-    def can_generate_metrics(self) -> bool:
-        return True
-
-    async def run_tts(self, text: str):
-        try:
-            await self.start_ttfb_metrics()
-
-            url = f"{self._base_url}"
-
-            url_query_params = []
-            if self._exaggeration is not None:
-                url_query_params.append(f"exaggeration={self._exaggeration}")
-            if self._cfg_weight is not None:
-                url_query_params.append(f"cfg_weight={self._cfg_weight}")
-
-            if len(url_query_params) > 0:
-                url += "?" + "&".join(url_query_params)
-
-            api_key = self._api_key or os.getenv("HATHORA_API_KEY")
-
-            form_data = aiohttp.FormData()
-            form_data.add_field("text", text)
-
-            if self._audio_prompt is not None:
-                form_data.add_field("audio_prompt", self._audio_prompt, filename="audio.wav", content_type="application/octet-stream")
-
-            yield TTSStartedFrame()
-
-            async with aiohttp.ClientSession() as session:
-                async with session.post(
-                    url,
-                    headers={"Authorization": f"Bearer {api_key}"},
-                    data=form_data,
-                ) as resp:
-                    audio_data = await resp.read()
-
-            await self.start_tts_usage_metrics(text)
-
-            pcm_audio, sample_rate, num_channels = _decode_audio_payload(
-                audio_data,
-                fallback_sample_rate=self.sample_rate or self._init_sample_rate or 24000,
-            )
-
-            await self.stop_ttfb_metrics()
-
-            frame = TTSAudioRawFrame(
-                audio=pcm_audio,
-                sample_rate=sample_rate,
-                num_channels=num_channels,
-            )
-
-            yield frame
-
-        except Exception as e:
-            logger.error(f"Hathora error: {e}")
-            yield ErrorFrame(f"Hathora error: {str(e)}")
-        finally:
-            await self.stop_ttfb_metrics()
-            yield TTSStoppedFrame()

src/pipecat/services/hathora/utils.py

@@ -0,0 +1,22 @@
+#
+# Copyright (c) 2024–2025, Daily
+#
+# SPDX-License-Identifier: BSD 2-Clause License
+#
+
+"""Utilities and types for [Hathora-hosted](https://models.hathora.dev) voice services."""
+
+from dataclasses import dataclass
+
+
+@dataclass
+class ConfigOption:
+    """Extra configuration option passed into model_config for Hathora (if supported by model).
+
+    Args:
+        name: Name of the configuration option.
+        value: Value of the configuration option.
+    """
+
+    name: str
+    value: str