livekit-agents@1.2.7

## What's Changed
* fix(examples): multi-user-translator: iterate over copy of keys to allow dict mutation during loop by @mike-r-mclaughlin in https://github.com/livekit/agents/pull/3190
* Add missing mistralai and smallestai optional dependencies by @bcherry in https://github.com/livekit/agents/pull/3191
* fix(google): Instant Voice Cloning Key Parameter is incorrect by @gnomefin in https://github.com/livekit/agents/pull/3203
* gemini live: create new generation only if response has a content by @longcw in https://github.com/livekit/agents/pull/3192
* Document text_type for Amazon Polly TTS by @kath0la in https://github.com/livekit/agents/pull/3200
* enable use_tts_aligned_transcript for non-streaming tts by default by @longcw in https://github.com/livekit/agents/pull/3206
* Fix Google STT Word‑timings error. by @itskyf in https://github.com/livekit/agents/pull/3204
* fix interruption context when speech has't started for session.say by @longcw in https://github.com/livekit/agents/pull/3207
* fix: only add meta to MCP tool schema when it's provided by @longcw in https://github.com/livekit/agents/pull/3212
* remove thinking_budget range check for google LLM by @longcw in https://github.com/livekit/agents/pull/3213
* Add `start_time`, `end_time`, and `speaker_id` to 11labs `SpeechData` by @dvschuyl in https://github.com/livekit/agents/pull/3224
* fix ElevenLabs stt base url configuration by @longcw in https://github.com/livekit/agents/pull/3228
* support updating `min_endpointing_delay` via AgentSession and configing it per-agent by @longcw in https://github.com/livekit/agents/pull/3227
* feat: enable keyterm prompting in deepgram for de, nl, sv, da by @danielgrittner in https://github.com/livekit/agents/pull/3215
* Plugin: add upliftai TTS plugin by @zaidqureshi2 in https://github.com/livekit/agents/pull/3209
* add readme for examples by @longcw in https://github.com/livekit/agents/pull/3225
* Update Anthropic LLM models by @olegkorol in https://github.com/livekit/agents/pull/3243
* chore: allow types-protobuf>=4 by @davidzhao in https://github.com/livekit/agents/pull/3247
* feat: add force parameter to interrupt methods for speech generation by @Panmax in https://github.com/livekit/agents/pull/3246
* fix groq plugin dependencies by @longcw in https://github.com/livekit/agents/pull/3256
* Add Soniox STT integration by @zanhorvat-soniox in https://github.com/livekit/agents/pull/2443
* feat: add option to tag audio events in ElevenLabs STT by @Panmax in https://github.com/livekit/agents/pull/3249
* fix: Google TTS empty results by @itskyf in https://github.com/livekit/agents/pull/3252
* add `cancel_tool_reply` to function_tools_executed event by @longcw in https://github.com/livekit/agents/pull/3177
* chore(11labs): update plugin to use multi-context websocket API by @davidzhao in https://github.com/livekit/agents/pull/3241
* add resume_false_interruption and pause/resume the audio output by @longcw in https://github.com/livekit/agents/pull/3109
* update silero vad to v6 model by @theomonnom in https://github.com/livekit/agents/pull/3275

## New Contributors
* @gnomefin made their first contribution in https://github.com/livekit/agents/pull/3203
* @itskyf made their first contribution in https://github.com/livekit/agents/pull/3204
* @dvschuyl made their first contribution in https://github.com/livekit/agents/pull/3224
* @danielgrittner made their first contribution in https://github.com/livekit/agents/pull/3215
* @zaidqureshi2 made their first contribution in https://github.com/livekit/agents/pull/3209
* @olegkorol made their first contribution in https://github.com/livekit/agents/pull/3243
* @zanhorvat-soniox made their first contribution in https://github.com/livekit/agents/pull/2443

**Full Changelog**: https://github.com/livekit/agents/compare/livekit-agents@1.2.6...livekit-agents@1.2.7