The error you're encountering, "`TypeError: __init__() got an unexpected keyword argument 'model'`," suggests that the TTS class you're using does not accept the parameter

model

. This discrepancy might be due to differences in the TTS implementation or library version. Here are some steps to resolve the issue: 1. Verify the exact TTS class you're using. For example, some implementations use

model_id

instead of

model

. 2. Ensure that your code matches the documentation for the specific version of the ElevenLabs TTS library you have installed. If the documentation specifies

model

, ensure you're using the latest version of the library. 3. If you're using an older version of the library, consider updating it to the latest version to align with the documentation. If you continue to face issues, please let me know, and I can assist further. Sources: ElevenLabs integration guide | LiveKit Docs | livekit.plugins.elevenlabs API documentation

The ElevenLabs TTS class accepts the following parameters: • model: String parameter (Optional, Default: "eleven_turbo_v2_5"). • voice: Configuration for the voice to use, which includes: ◦ id: Voice identifier. ◦ name: Voice name. ◦ category: Voice category. ◦ settings: Voice settings including stability, similarity_boost, style, and use_speaker_boost. • language: Language code (e.g., "en"). • streaming_latency: Integer value (e.g., 3). • enable_ssml_parsing: Boolean value. • chunk_length_schedule: Array of integers (e.g., [80, 120, 200, 260]). Additional parameters from the TTSOptions interface include: • apiKey: Optional string. • baseURL: String. • encoding: TTSEncoding type. • modelID: String. Ensure that your implementation aligns with these parameters to avoid errors. Let me know if you need further clarification! Sources: ElevenLabs integration guide | LiveKit Docs | TTSOptions | LiveKit Agents

The error "`TypeError: __init__() got an unexpected keyword argument 'language'`" suggests that the

language

parameter might not be supported in the way you're using it. Here are some key points to consider: • The

language

parameter is only valid when using the

"eleven_turbo_v2_5"

model. If you're using a different model, this parameter may not be supported. • If you're not using

"eleven_turbo_v2_5"

, try removing the

language

parameter from your code. • Ensure that your ElevenLabs TTS library is updated to the latest version, as older versions might not support this parameter. Let me know if you need further assistance! Sources: livekit.plugins.elevenlabs API documentation

Here is an example of how to use the ElevenLabs TTS with

model_id

and

language

parameters:

from livekit import agents, rtc
from livekit.agents.tts import SynthesizedAudio
from livekit.plugins import elevenlabs
from typing import AsyncIterable

ctx: agents.JobContext = ...
text_stream: AsyncIterable[str] = ...
audio_source = rtc.AudioSource(44100, 1)

track = rtc.LocalAudioTrack.create_audio_track("agent-audio", audio_source)
await ctx.room.local_participant.publish_track(track)

# Initialize ElevenLabs TTS with model_id and language
tts = elevenlabs.TTS(model_id="eleven_turbo_v2", language="en")
tts_stream = tts.stream()

# Create a task to consume and publish audio frames
ctx.create_task(send_audio(tts_stream))

# Push text into the stream
async for text in text_stream:
    tts_stream.push_text(text)
tts_stream.end_input()

Alternatively, for a more detailed initialization:

eleven_tts = elevenlabs.tts.TTS(
    model="eleven_turbo_v2_5",
    voice=elevenlabs.tts.Voice(
        id="EXAVITQu4vr4xnSDxMaL",
        name="Bella",
        category="premade",
        settings=elevenlabs.tts.VoiceSettings(
            stability=0.71,
            similarity_boost=0.5,
            style=0.0,
            use_speaker_boost=True
        ),
    ),
    language="en",
    streaming_latency=3,
    enable_ssml_parsing=False,
    chunk_length_schedule=[80, 120, 200, 260],
)

Let me know if you need further assistance! Sources: ElevenLabs integration guide | LiveKit Docs | livekit.plugins.elevenlabs API documentation | Working with plugins | LiveKit Docs

I'm sorry, but I don't have the information you need at the moment. If you would like a member of the LiveKit team to respond, please ask your question in one of the other channels.