wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rime: pass aiohttp session to constructor

Browse Source
This commit is contained in:
Aleix Conchillo Flaqué
2025-02-19 22:21:02 -08:00
parent 6809254963
commit 69e6f3fdb7
2 changed files with 25 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
CHANGELOG.md
View File

@@ -17,6 +17,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
### Changed ### Changed
- `RimeHttpTTSService` needs an `aiohttp.ClientSession` to be passed to the
constructor as all the other HTTP-based services.
- `RimeHttpTTSService` doesn't use a default voice anymore.
- `DeepgramSTTService` now uses the new `nova-3` model by default. If you want - `DeepgramSTTService` now uses the new `nova-3` model by default. If you want
to use the previous model you can pass `LiveOptions(model="nova-2-general")`. to use the previous model you can pass `LiveOptions(model="nova-2-general")`.
(see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api) (see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)

41
src/pipecat/services/rime.py
View File

@@ -345,7 +345,8 @@ class RimeHttpTTSService(TTSService):
self, self,
*, *,
api_key: str, api_key: str,
voice_id: str = "eva", voice_id: str,
aiohttp_session: aiohttp.ClientSession,
model: str = "mistv2", model: str = "mistv2",
sample_rate: Optional[int] = None, sample_rate: Optional[int] = None,
params: InputParams = InputParams(), params: InputParams = InputParams(),
@@ -354,6 +355,7 @@ class RimeHttpTTSService(TTSService):
super().__init__(sample_rate=sample_rate, **kwargs) super().__init__(sample_rate=sample_rate, **kwargs)
self._api_key = api_key self._api_key = api_key
self._session = aiohttp_session
self._base_url = "https://users.rime.ai/v1/rime-tts" self._base_url = "https://users.rime.ai/v1/rime-tts"
self._settings = { self._settings = {
"speedAlpha": params.speed_alpha, "speedAlpha": params.speed_alpha,
@@ -388,30 +390,27 @@ class RimeHttpTTSService(TTSService):
try: try:
await self.start_ttfb_metrics() await self.start_ttfb_metrics()
async with aiohttp.ClientSession() as session: async with self._session.post(
async with session.post(self._base_url, json=payload, headers=headers) as response: self._base_url, json=payload, headers=headers
if response.status != 200: ) as response:
error_message = f"Rime TTS error: HTTP {response.status}" if response.status != 200:
logger.error(error_message) error_message = f"Rime TTS error: HTTP {response.status}"
yield ErrorFrame(error=error_message) logger.error(error_message)
return yield ErrorFrame(error=error_message)
return
await self.start_tts_usage_metrics(text) await self.start_tts_usage_metrics(text)
yield TTSStartedFrame() yield TTSStartedFrame()
# Process the streaming response # Process the streaming response
chunk_size = 8192 chunk_size = 8192
first_chunk = True
async for chunk in response.content.iter_chunked(chunk_size): async for chunk in response.content.iter_chunked(chunk_size):
if first_chunk: if chunk:
await self.stop_ttfb_metrics() await self.stop_ttfb_metrics()
first_chunk = False frame = TTSAudioRawFrame(chunk, self.sample_rate, 1)
yield frame
if chunk:
frame = TTSAudioRawFrame(chunk, self.sample_rate, 1)
yield frame
except Exception as e: except Exception as e:
logger.exception(f"Error generating TTS: {e}") logger.exception(f"Error generating TTS: {e}")
yield ErrorFrame(error=f"Rime TTS error: {str(e)}") yield ErrorFrame(error=f"Rime TTS error: {str(e)}")