Talky Talky (shawnrushefsky/talky-talky) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 92 tools. No publisher has claimed this listing.

Caution

54/100

Talky Talky

Item: Talky Talky
Rating: 54
Author: M8ven

A comprehensive audio MCP server that enables AI agents to generate speech, transcribe audio, clone voices, analyze speech quality, design soundscapes, and manage audio assets through a standardized interface.

→ shawnrushefsky/talky-talky · listed on glama

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every push why connect →

Who stands behind it

shawnrushefsky

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

Glamanot scored here

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings

✅

No credential exfiltration, no sensitive file access, no obfuscation

Static analysis found nothing flowing your secrets to unexpected places.

✅

Open source with a license and README

Anyone can audit the code, the license is declared, and the publisher documents what it does.

// tools this server exposes92 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

analyze_emotion

Detect emotion in speech.

analyze_voice_similarity

Compare two audio files for voice similarity.

extract_voice_embedding

Extract 256-dim voice embedding vector for comparison.

analyze_speech_quality

Assess speech quality (MOS 1-5 scale).

verify_tts_comprehensive

Comprehensive TTS verification: text, voice, emotion, quality.

detect_spoken_tts_tags

Detect if TTS verbalized emotion tags instead of expressing them.

convert_emotion_tags

Convert emotion tags between TTS engine formats.

find_speech_onset

Find where speech actually begins in audio.

detect_audio_truncation

Check if TTS output was truncated mid-sentence.

verify_audio_segment_boundaries

Verify audio has proper speech boundaries.

smart_trim_to_speech

Trim audio to speech boundaries with natural padding.

analyze_audio_loudness

Analyze loudness: peak, RMS, LUFS, dynamic range, true peak.

detect_audio_clipping

Detect digital clipping (distortion).

analyze_audio_spectrum

Analyze frequency content: dominant freq, centroid, bandwidth, energy.

detect_audio_silence

Detect silence regions in audio.

validate_audio_format

Validate audio format against requirements.

list_asset_sources

List available audio asset sources (local, freesound, jamendo).

search_audio_assets

Search audio assets across sources.

get_audio_asset

Get detailed info about an asset (format: source:id).

download_audio_asset

Download an asset to local storage.

import_audio_folder

Import audio files from folder into asset library.

configure_freesound_api

Configure Freesound.org API key.

configure_jamendo_api

Configure Jamendo API client ID.

set_audio_library_path

Set asset library location (or "default" to reset).

get_audio_library_path

Get current asset library path.

add_asset_tags

Add tags to an asset for organization.

remove_asset_tags

Remove tags from an asset.

list_all_asset_tags

List all tags in library with usage counts.

list_indexed_audio_folders

List folders that have been indexed for assets.

rescan_audio_folder

Rescan indexed folder for new/modified files.

remove_indexed_audio_folder

Remove folder from index (doesn't delete files).

check_autotag_availability

Check available AI auto-tagging capabilities.

auto_tag_audio_asset

Auto-tag asset using AI analysis (transcription, emotion, quality).

get_audio_file_info

Get audio file info: format, duration, sample rate, channels.

set_output_directory

Set default output directory for generated audio.

get_output_directory

Get current default output directory.

check_ffmpeg_available

Check if ffmpeg is installed.

play_audio

Play audio in system default player.

convert_audio_format

Convert audio to different format (mp3, wav, m4a).

resample_audio_file

Resample audio to target sample rate (24000, 44100, 48000 Hz).

check_audio_compatibility

Check if audio files are compatible for joining.

join_audio_files

Concatenate audio files with optional gaps.

crossfade_join_audio

Join audio files with crossfade transitions.

trim_audio_file

Trim audio to boundaries or auto-detect content.

batch_trim_audio_files

Trim multiple audio files to content boundaries.

batch_analyze_silence

Detect silence in multiple audio files.

insert_audio_silence

Add silence before/after audio.

generate_silence_audio

Generate a silent audio file.

normalize_audio_levels

Normalize audio to broadcast standard (-16 LUFS).

batch_normalize_audio_files

Normalize multiple audio files to -16 LUFS.

normalize_sfx_to_level

Normalize audio to specific LUFS level.

batch_normalize_sfx_to_lufs

Normalize multiple files to target LUFS.

mix_audio_tracks

Mix tracks together (simultaneous playback).

overlay_audio_track

Overlay one track on another at specific position.

overlay_multiple_tracks

Overlay multiple tracks with individual positions and volumes.

loop_audio_to_target_duration

Loop audio to reach target duration.

adjust_audio_volume

Adjust volume (multiplier or dB).

apply_audio_fade

Apply fade in/out effects.

get_audio_mean_level

Get mean audio level in dBFS.

compare_audio_levels

Compare loudness levels across multiple files.

apply_audio_effects

Apply audio effects: filters, EQ, speed, reverb, echo.

shift_audio_pitch

Shift pitch without changing speed. +12 = octave up.

stretch_audio_time

Change duration without changing pitch. 0.5 = half speed, 2 = double.

apply_voice_effect_preset

Apply voice effect preset.

list_voice_effects

List available voice effect presets.

shift_voice_formant

Shift voice formants. <1 = masculine, >1 = feminine.

autotune_vocals

Apply pitch correction to vocals.

detect_vocal_pitch

Detect pitch in audio. Returns frequency stats and detected notes.

list_autotune_scales

List available scales for autotune.

list_autotune_keys

List available keys for autotune.

capabilities

Get a summary of all available capabilities.

check_availability

Check if engines are available and properly configured.

get_engines_info

Get detailed info about engines in a subsystem.

list_available

List available engines in a subsystem.

generate_song_levo

Generate a song with LeVo (Tencent SongGeneration).

generate_song_acestep

Generate a song with ACE-Step (MPS + CUDA).

get_songgen_model_status

Get download status of song generation models.

download_songgen_models

Download LeVo song generation models (~10GB).

get_acestep_model_status

Get download status of ACE-Step models.

download_acestep_models

Download ACE-Step models (~7GB).

get_songgen_lyrics_format

Get lyrics format guide for song generation.

transcribe_audio

Transcribe audio to text.

transcribe_with_timestamps

Transcribe with detailed timing info.

verify_tts_output

Verify TTS audio contains expected text.

speak

batch_speak

Generate TTS for multiple text segments.

get_tts_model_status

Get download status of Maya1 and SNAC models.

download_tts_models

Download Maya1 TTS models (~10GB total).

get_tts_engine_info

Get info about all TTS engines and their parameters.

create_audiobook_chapter

Generate TTS for multiple segments, join, and normalize.

create_podcast_with_music

Create podcast with intro/outro music and optional background.

create_sound_effect_scene

Create a soundscape with ambient base and timed sound effects.

// environment variables

To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.

configSONGGEN_CACHE_DIR

configHF_HOME

// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

92/92 tools missing one or more hints — analyze_emotion (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze_voice_similarity (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); extract_voice_embedding (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +89 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Destructive tools are labelled

3 tools perform destructive updates without destructiveHint — create_audiobook_chapter deletes at line 110 (shutil.rmtree(temp_dir, ignore_errors=True)); create_podcast_with_music deletes at line 219 (shutil.rmtree(temp_dir, ignore_errors=True)); create_sound_effect_scene deletes at line 294 (shutil.rmtree(temp_dir, ignore_errors=True))

Add destructiveHint:true to any tool whose handler calls .delete(), .upsert(), .update(), unlink, rm, DELETE, DROP, REPLACE INTO, or any operation that overwrites existing data.

Tool inputs are validated

77/92 tool handlers declare input schemas (84%)

Declare an inputSchema with zod/joi/yup on every tool definition.

Tool handlers catch errors

Only 4/92 tool handlers wrap calls in try/catch (4%)

Wrap each tool handler body in try/catch and return a structured error response.

Tests exist

No test files found

Add tests that exercise each declared tool.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail

The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.

// improvement guidance — verified publishers only

We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.

// embed badge in your README

[![M8ven Verified](https://m8ven.ai/badge/mcp/shawnrushefsky/talky-talky?variant=verified)](https://m8ven.ai/mcp/shawnrushefsky/talky-talky)

Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.

commit: d92b65e68aec8d70946b0724d576aa1600b09cc4

code hash: 549e997808fdf8de9794f3b54d1fd881d4a5e58c1345a9f054d812dc1111645c

view raw JSON →

Check MCPs from inside your assistant

Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check

check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern

How to add it →Free · no account needed · works in any MCP client