Skip to main content
Glama
jagones84

mcp-voice-studio

by jagones84
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
HF_TOKENYesHugging Face access token required to download OmniVoice and tokenizer models. Get one at https://huggingface.co/settings/tokens
VOICESTUDIO_VENVYesAbsolute path to the VoiceStudio virtual environment (e.g., /home/user/Repositories/VoiceStudio/.venv)
CUDA_VISIBLE_DEVICESNoOptional CUDA device selection (e.g., '0' or '0,1'). Used to restrict the GPU used by the engine.

Instructions

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Capabilities

Features and capabilities supported by this server

Protocol revision2025-11-25

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
tool_clone_voice_from_audioA

Save a voice profile from a reference audio (5-30s WAV ideal).

Two input modes (EITHER ref_audio_path OR audio_url must be provided, not both): A) Local file: pass ref_audio_path='/path/to/sample.wav'. B) URL clip: pass audio_url='https://youtu.be/...', ts=30, tf=45. yt-dlp downloads the audio and ffmpeg slices [ts, tf] into a 24kHz mono 16-bit PCM WAV, which is then used as the reference.

Workflow:

  1. Pick a clean 5-30s speech sample (local file OR URL clip).

  2. Write the exact transcript in ref_text.

  3. Pick a memorable voice_name (used later as voice_name= in synthesize_speech).

  4. Returns a dict with 'status', 'voice_name', 'profile_path', 'ref_audio_path', and (for URL mode) 'source_url', 'ts', 'tf', 'clip_duration_s'.

Common errors:

  • both ref_audio_path and audio_url provided: pick one.

  • voice_exists: pass overwrite=True or pick a different voice_name.

  • bad local path: check the path exists and is readable.

  • bad URL: yt-dlp/ffmpeg failure will be reported in the raised RuntimeError.

tool_synthesize_speechA

Generate speech audio with a cloned voice (from voice_name) OR voice design (from instruct), or both.

Three usage modes:

  1. Cloned voice: pass voice_name='claudia_asmr', omit instruct.

  2. Voice design: pass instruct='whisper, female, low pitch', omit voice_name.

  3. Hybrid: pass both voice_name AND instruct to add style to a cloned voice.

Returns dict with: output_path, duration_s, sample_rate, channels, model, voice_name, generation_time_s, and (if any ASMR effect ran) asmr_applied.

ASMR pipeline: highpass(60Hz) -> lowpass -> stereo_pan -> reverb -> binaural -> padding. All ASMR params default to OFF (passthrough). Output is stereo whenever any stereo-capable effect (stereo_pan, reverb, binaural_beat_hz) is active.

tool_design_voiceA

Generate speech using voice design keywords only (no cloned voice).

Same ASMR params as synthesize_speech. Use this when you want a one-off voice without persisting a profile. For reusable voices, clone first with clone_voice_from_audio then call synthesize_speech with voice_name.

tool_list_voicesA

List all saved voice profiles.

Returns: list of dicts, each with 'name', 'description', 'language', 'source', 'created_at'. Use this to discover available voice_name values before calling synthesize_speech.

tool_get_voice_infoA

Get full metadata of a single saved voice profile: name, description, language, ref_audio_path, ref_text, created_at.

Use this to verify a profile exists and inspect its reference audio path before calling synthesize_speech with that voice_name.

tool_delete_voiceA

Delete a voice profile and its reference audio file. Cannot be undone.

Use this to free disk space or clean up test voices. The voice will no longer appear in list_voices and synthesize_speech with this voice_name will fail.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.4/5.0

Scored across 6 tools

Disambiguation3/5

Profile management tools (list/get/delete) are clearly distinct, and clone/synthesize have clear roles. However, design_voice overlaps with synthesize_speech because synthesize_speech also supports voice design via the instruct parameter; the descriptions mitigate this, but an agent could still be unsure which to call.

Naming Consistency5/5

All tool names follow a consistent tool_verb_noun snake_case pattern, with each verb clearly indicating the action. The minor noun variation between 'voice' and 'speech' is natural and does not create confusion.

Tool Count5/5

Six tools is a well-scoped size for a voice cloning and synthesis server. Each tool contributes to a clear lifecycle: profile creation, inspection, deletion, and audio generation.

Completeness5/5

The server covers the full voice-profile lifecycle: create via clone, read via list and get info, delete, and use for speech synthesis. It also offers a one-off design path, leaving no obvious critical gaps for its stated purpose.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources