audio-language-models
Gemini Live API, Grok Voice Agent, GPT-4o-Transcribe, AssemblyAI patterns for real-time voice, speech-to-text, and TTS. Use when implementing voice agents, audio transcription, or conversational AI.
npx skills add majiayu000/claude-skill-registry --skill audio-language-models --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Audio Language Models (2026) Build real-time voice agents and audio processing using the latest native speech-to-speech models. ## When to Use - Real-time voice assistants and agents - Live conversational AI (phone agents, support bots) - Audio transcription with speaker diarization - Multilingual voice interactions - Text-to-speech generation - Voice-to-voice translation ## Model Comparison (January 2026) ### Real-Time Voice (Speech-to-Speech) | Model | Latency | Languages | Price | Best For | |-------|---------|-----------|-------|----------| | **Grok Voice Agent** | <1s TTFA | 100+ | $0.05/min | Fastest, #1 Big Bench | | **Gemini Live API** | Low | 24 (30 voices) | Usage-based | Emotional awareness | | **OpenAI Realtime** | ~1s | 50+ | $0.10/min | Ecosystem integration | ### Speech-to-Text Only | Model | WER | Latency | Best For | |-------|-----|---------|----------| | **Gemini 2.5 Pro** | ~5% | Medium | 9.5hr audio, diarization | | **GPT-4o-Transcribe** | ~7% | Medium | Accuracy + accents | | **AssemblyAI Universal-2** | 8.4% | 200ms | Best features | | **Deepgram Nova-3** | ~18% | <300ms | Lowest latency | | **Whisper Large V3** | 7.4% | Slow | Self-host, 99+ langs | ## Grok
- When to Use
- Model Comparison (January 2026)
- Real-Time Voice (Speech-to-Speech)
- Speech-to-Text Only
- Grok Voice Agent API (xAI) - Fastest
- Gemini Live API (Google) - Emotional Awareness
- Gemini Audio Transcription (Long-Form)
- Gemini TTS (Text-to-Speech)
- OpenAI GPT-4o-Transcribe
- AssemblyAI (Best Features)
- Real-Time Streaming Comparison
- API Pricing (January 2026)
- Key Decisions
- Common Mistakes
What does the audio-language-models skill do?
Gemini Live API, Grok Voice Agent, GPT-4o-Transcribe, AssemblyAI patterns for real-time voice, speech-to-text, and TTS. Use when implementing voice agents, audio transcription, or conversational AI.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill audio-language-models --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.