voice▌

Voice cloning and text-to-speech synthesis using Alibaba Cloud Qwen TTS VC models. \n \n Supports two model variants: standard batch processing ( qwen3-tts-vc-2026-01-22 ) and real-time streaming ( qwen3-tts-vc-realtime-2026-01-15 ) \n Accepts voice samples as file paths or raw bytes; generates cloned voice IDs for reuse across multiple synthesis requests \n Normalized interface handles text input, voice enrollment, optional streaming output, and returns audio URLs or PCM chunks \n Requires DASH

Natural conversation with AI through speech, balancing latency against control. \n \n Choose between speech-to-speech models (lowest latency, less controllable) or pipeline architectures (STT→LLM→TTS for fine-grained control) \n Core challenges: latency budgeting across all components, voice activity detection, barge-in handling, and turn-taking to avoid awkward pauses or overlaps \n Requires semantic VAD, response length constraints in prompts, and noise handling to achieve natural conversation

Extract and document a writer's distinctive voice patterns for consistent reproduction. Creates a "voice guide" that enables authentic writing that sounds like the source, not a generic approximation.

This skill guides you through building production-ready voice AI engines with real-time conversation capabilities. Voice AI engines enable natural, bidirectional conversations between users and AI agents through streaming audio processing, speech-to-text transcription, LLM-powered responses, and text-to-speech synthesis.

Category: test

Use the voice-call plugin to start or inspect calls (Twilio, Telnyx, Plivo, or mock).

Natural AI voice generation across seven models with 22+ voices, multiple languages, and emotional range. \n \n Supports ElevenLabs (premium quality, 32 languages), Kokoro TTS, DIA, Chatterbox, Higgs, and VibeVoice, each optimized for different styles from professional narration to casual conversation \n Includes 16+ named voices with gender and style profiles (e.g., warm, authoritative, youthful) plus speed control (0.8–1.2x) and punctuation-based pacing \n Handles multi-voice conversations, lo

Generate natural AI voices via inference.sh CLI.

Category: test

Category: provider