using elevenlabs, was working fine and since some days it is saying the first sentence only, the rest is not said/speaking

Thanks for reaching out, Mostafa. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.

i did not set

chunkLengthSchedule

,

enable_ssml_parsing

is there a mandatory props i need to set?

Thanks — regarding required properties for ElevenLabs TTS: • Mandatory: ◦ API key (your ElevenLabs credential used by the plugin) ◦

voice_id

◦

model

◦ the text string you want synthesized • Optional (have sensible defaults): ◦

chunkLengthSchedule

— optional; defaults like

[80, 120, 200, 260]

are typical. Set it only if you’re tuning streaming chunk sizes. ◦

enable_ssml_parsing

— optional; defaults to off. Try disabling it if you’re not sending SSML. ◦

streaming_latency

and other tuning params — optional. If you haven’t set

chunkLengthSchedule

or

enable_ssml_parsing

, that’s fine — they’re not mandatory. To troubleshoot the “only first sentence spoken” issue, explicitly set conservative defaults and test:

from livekit.plugins import elevenlabs

tts = elevenlabs.TTS(
    model="eleven_multilingual_v2",
    voice_id="your_voice_id",
    chunk_length_schedule=[80, 120, 200, 260],
    enable_ssml_parsing=False
)

# pass a multi-sentence string to synthesize

If the problem persists after trying the above, please share your platform (Web/Node/Python), the exact

model

and

voice_id

you’re using, and a short sample text that reproduces the issue.