Integration

Voicemaker integration

Voicemaker is a text-to-speech platform. Generate speech from text (up to 10,000 characters, SSML on AI1 to AI4 voices) with hundreds of voices and optional VoxFX sound effects, list voices and effect presets, clone a voice from a recording and manage the clones, re-voice an audio file with speech to speech, and transcribe audio to text or SRT subtitles. Generated audio comes back as a download URL kept on Voicemaker's server for FileStore hours. Calls consume the characters or credits of your Voicemaker plan. Not exposed: the streaming response type and the two WebSocket APIs. Authentication is a Voicemaker API key (developer.voicemaker.in, Dashboard, API keys) sent as Authorization: Bearer <key>.

Connect Voicemaker How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Voicemaker.Built from the 12 Voicemaker tools below, on the connection you add once.

What you can do with Voicemaker

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Voice clone, 4 operations

delete_voice_cloneDelete voice cloneDELETEPermanently deletes a voice clone and its stored samples. Irreversible.
edit_voice_cloneEdit voice clonePUTEdits a voice clone's name, description or labels; the voice itself cannot change (delete and clone again for that). Leave a field out to keep it.
get_voice_cloneGet voice cloneGETReturns one voice clone's metadata (name, description, labels, engine) by VoiceId.
list_voice_clonesList voice clonesGETLists the voice clones of your account with VoiceId, name, description and labels, paginated (5 per page by default).

Speech to text, 3 operations

get_transcriptionGet transcriptionGETReturns one transcription job from the last hour: status (completed, pending or failed; pending over 15 minutes fails), generatedText and charge.
list_transcriptionsList transcriptionsGETLists the transcription jobs of the last hour with status, text and charge, paginated.
transcribe_audioTranscribe audioPOSTTranscribes an audio file. Files up to 3 minutes come back done in data.generatedText; longer ones return isProcessing true: read get_transcription with data.taskId. 5 credits per second.

Add, 1 operation

create_voice_cloneCreate voice clonePOSTCreates a voice clone from one recording (mp3, wav or mp4, 20 seconds to 30 minutes) and returns its VoiceId. Needs a paid plan with a free clone slot; the clone may take minutes to be usable.

List, 1 operation

list_voxfx_presetsList voxfx presetsGETLists the VoxFX effect presets by category, with each preset's presetId and the effects (with ranges and defaults) you can override in generate_speech VoxFx.

Speech, 1 operation

generate_speechGenerate speechPOSTConverts text to speech; returns path, a URL of the audio (kept FileStore hours), and characters used and left. Charged per character, 2x to 4x on ProPlus voices (ProEngine). VoxFx adds an effect preset.

Speech to speech, 1 operation

convert_speech_to_speechConvert speech to speechPOSTRe-voices an audio file with a ProPlus or cloned voice, keeping its timing; returns path, a URL of the new audio. Billed 100 credits per second of audio.

Voice, 1 operation

list_voicesList voicesPOSTLists the available stock voices (clones excluded) with VoiceId, engine, gender, language and supported effects. Filter by language, or multi-lang for Pro voices.

Use Voicemaker from Claude Code, Cursor or Codex

Connect Voicemaker in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Voicemaker operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Voicemaker

Create your workspace
Sign up free. Nothing to install.
Connect Voicemaker once
Add your Voicemaker connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.