"Building voice agents and controlling SIP phones" matching MCP servers:

Build AI voice agents that answer and place real phone calls over your own carrier, on any voice engine (Gemini Live, Sarvam, OpenAI, ElevenLabs and more) with one API key. Create agents, connect SIP trunks and numbers, run call campaigns, and read transcripts and costs from Claude Code, Codex, Cursor or any MCP client.

Exposes push-to-talk speech tools to an agent: check whether the offline ASR daemon is ready, wait for the user to confirm something aloud without auto-submitting that utterance, and interrupt the current turn when the user speaks a stop phrase.

Enables text-to-speech and speech-to-text through MCP tools, using Groq's free hosted endpoints when configured and falling back to fully local keyless models otherwise. Also provides voice listing and provider health checks.

Give your AI agent a voice with x402 pay-per-call speech synthesis, offering 20 voices, 10 personas, 31 languages, and granular controls.

Enables text-to-speech audio generation using ElevenLabs voices directly from Claude conversations, supporting single and batch conversion, voice listing, and voice ID lookup.

Enables an AI assistant to have its recent code actions summarized aloud through system speakers, using offline native voices or cloud neural voices. It supports asynchronous playback and voice listing so users can hear what the agent did without reading the full response.

Enables MCP clients to submit completed speech or typed text to a self-hosted decision engine and receive judgments such as ordinary speech, command, retained thought, uncertainty, or no action, along with session and decision inspection.

Voice Mode for Claude Code

Enables ChatGPT on the web to generate and play spoken audio through an embedded player, exposing a speak tool that renders text with selectable styles and scenes via configurable text-to-speech providers. It routes each request across ElevenLabs, Cartesia, Azure Speech, and DashScope in a configured failover order, picking providers by language and scenario.

Enables AI agents to place VoIP phone calls via Asterisk, play TTS messages, capture DTMF input, and optionally record and transcribe voice responses.

Enables MCP clients to speak by running local voice models using Chatterbox Turbo TTS or Kokoro TTS, with support for voice cloning, paralinguistic tags, and multiple voices.

Enables AI assistants to synthesize speech with custom or cloned ElevenLabs voices and display an inline audio player with waveform visualization, transcript toggle, and dark mode support.

Local voice and AI platform for macOS offering speech recognition, speech synthesis, MLX-based inference, OpenAI-compatible APIs, and MCP tools for use as an assistant or integration gateway.

Enables AI agents to submit and manage durable long-form audio transcription jobs, and read or export structured transcripts via MCP tools.

An MCP server for AI voice synthesis with an inline audio player, allowing users to give their AI assistant a custom cloned voice using DashScope or ElevenLabs.

Enables AI assistants to synthesize speech using a custom cloned voice through MiniMax TTS and present it in an inline audio player with waveform visualization and transcript controls.

Enables AI assistants to synthesize speech in a custom cloned voice and present it through an inline audio player with waveform visualization and transcript toggle.

MCP server for Vietnamese text-to-speech with voice cloning, 10 built-in voices, text normalization, and long-form queuing, running 100% locally.

Enables hands-busy small online sellers to use voice-driven MCP tools for deterministic margin and listing checks and to draft ad headlines, 30-second shorts scripts, and detail page outlines.

Enables Alexa+ clients to monitor live calls for voice-clone and scam-pressure risk, verify a caller with a real family member, review alert history, and reset call state through MCP tools.

Enables macOS users to hear short spoken summaries of agent replies using the built-in say command, while keeping full details in the chat. Works with any MCP-compatible host and requires no cloud or API key.

Enables AI coding assistants to verbally announce task progress and events through local text-to-speech, with cloud synthesis via Volcano Engine or Edge TTS, scene-based voice settings, and a Windows SAPI fallback so announcements continue even when the cloud fails.

Enables bidirectional voice interaction for Claude Code using local speech-to-text and text-to-speech models optimized for Apple Silicon. It provides tools to listen to user speech via microphone and speak responses aloud through system speakers.

Transcribe voice messages to text and generate spoken audio from text, served as cached Ogg/Opus files for instant playback.

Provides local text-to-speech output to PC speakers, Telegram voice messages, or MP3 files, and transcribes voice messages locally or via cloud. Includes tools for checking playback status, stopping audio, and replying to Telegram messages.

Enables voice interaction with Claude Code through local speech-to-text (Whisper) and text-to-speech (Supertonic), allowing verbal input/output without external API calls.

MCP server that lets Claude place outbound telephone calls via ElevenLabs Agents over a SIP trunk and report the outcome including status, success evaluation, summary, and transcript.

Enables spoken conversations with Claude on a Mac: Claude speaks through speakers, listens to the user's natural replies, and transcribes them locally. No audio leaves the computer, and it includes tools for voice setup and a hands-free voice mode.

Give Claude ears: a local MCP server that records your mic and measures singing pitch (cents, vibrato, MIDI alignment), English pronunciation phoneme by phoneme, and public-speaking pace, pauses and filler words. Audio is analyzed on your computer with open models; a bundled skill turns Claude into a voice coach that tracks your progress.

Enables AI agents to synthesize natural speech using either platform system voices or premium OpenAI TTS, with automatic engine selection and graceful fallback.