Run any Skill in Manus with one click

audiocpp-voice-clone

Stars46

Forks6

UpdatedJuly 20, 2026 at 18:58

Clone a voice from a user-supplied reference clip and synthesize speech with it, by calling the raw audio.cpp TTS engine with voice_ref/reference_text — fields the built-in GuideAnts audio tools do not expose. Use when the user wants generated speech to sound like their own voice or another consenting speaker's recording.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

Elumenotion

Elumenotion/GuideAnts

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

File Explorer

3 files

SKILL.md

readonly

name	audiocpp-voice-clone
description	Clone a voice from a user-supplied reference clip and synthesize speech with it, by calling the raw audio.cpp TTS engine with voice_ref/reference_text — fields the built-in GuideAnts audio tools do not expose. Use when the user wants generated speech to sound like their own voice or another consenting speaker's recording.
metadata	{"guideants":{"enabled":true,"display_order":31,"requires_toolsets":["sandbox"]}}

audio.cpp voice cloning (experimental)

The GuideAnts TTS wrapper only accepts {text, voice, speed}, but the real audiocpp_server engine it spawns (on 127.0.0.1:18084) accepts a reference clip for cloning. This skill calls that engine directly. Deliverables are WAV files in Output/; nothing here touches the live phone/voice path.

Consent rule (read first)

Cloning from a reference clip is a supported, intended use when the speaker consents: the user states the clip is their own voice, or that they have the speaker's permission. In that case proceed — do not refuse consented cloning as a "security risk". Decline only when the request is to imitate a third party without consent (a celebrity, a colleague, a public figure), and say that consent is the missing piece.

Preflight

python3 Output/Skills/audiocpp-voice-clone/scripts/preflight.py --for voice-clone

Trust its verdict over this document. open: false usually means no TTS model is loaded — ask the user to load one via GuideAnts Settings → Local models. A warning about the loaded model's family means voice_ref may be rejected; chatterbox (the clon-task catalog model) is the known-good family.

Cloning

The reference clip must be a file in the workspace (e.g. an upload under Output/uploads/). Same container filesystem, so the engine reads it by path:

python3 Output/Skills/audiocpp-voice-clone/scripts/engine_tool.py speech \
  "Text to speak in the cloned voice" \
  -o Output/cloned.wav \
  --voice-ref Output/uploads/user_voice.wav \
  [--reference-text "transcript of the reference clip"] \
  [--seed 42]

The engine model id is auto-detected from the wrapper's /health (catalogEntryId); no flag needed.
--reference-text helps families that want the reference transcript.
--seed makes the synthesis reproducible.
The engine errors loudly on options the loaded family doesn't support — surface that error text to the user; it is usually self-explanatory.

Verifying

Transcribe the result back and check it matches the input text (the ASR engine at 127.0.0.1:18082 accepts workspace paths):

python3 Output/Skills/audiocpp-voice-clone/scripts/engine_tool.py transcribe Output/cloned.wav

When this skill isn't enough

Loaded model rejects voice_ref → ask the user to load chatterbox via Settings, or use the audiocpp-deferred-tts skill (several deferred families also clone from reference audio).
No TTS model loaded at all and the user can't load one → blocked; say so.

Reporting

End by telling the user what worked and what was blocked, quoting the preflight/engine evidence, so the experiment log stays honest.

More from this repository

same repository

audiocpp-asr-extended

Elumenotion/GuideAnts

Transcription beyond the GuideAnts wrapper contract: transcribe workspace files by path (no upload, no 50 MB gateway cap), pass language hints, and sideload other qwen3-family ASR snapshots from Hugging Face through the wrapper. Use when a transcription needs a language hint, the file is large, or the user wants to try an ASR model the catalog doesn't list.

2026-07-2046

audiocpp-deferred-tts

Elumenotion/GuideAnts

Run TTS model families audio.cpp supports but GuideAnts does not ship — Qwen3 CustomVoice builtin speakers, VibeVoice multi-speaker dialogue, MioTTS, VoxCPM2, PocketTTS, Vevo2 voice conversion — by downloading the model and spawning a private audiocpp_server in the sandbox. Use when the user names one of these models or asks for a TTS capability the loaded catalog model rejects.

2026-07-2046

audiocpp-diarize

Elumenotion/GuideAnts

Speaker diarization: figure out who spoke when in a recording and produce a speaker-labeled transcript, by spawning a private audio.cpp engine with the sortformer diarization model and labeling each turn with the local ASR engine. Use when the user asks to diarize a meeting or call recording, separate or identify speakers, or wants a transcript broken down by speaker.

2026-07-2046

audiocpp-host-tts

Elumenotion/GuideAnts

Synthesize speech against the user's own host-native audiocpp_server build (outside the GuideAnts container) — including model families the container binary lacks, like Kokoro or Parakeet forks. TTS only. Use when the user says they run their own audio.cpp server or asks for a family the container build cannot load.

2026-07-2046

audiocpp-extended

Elumenotion/GuideAnts

Experimental: use audio.cpp scenarios and models that GuideAnts does not ship — speaker diarization (who spoke when, speaker-labeled transcripts), voice cloning from user-supplied audio, deterministic seeds, builtin speakers, language forcing, and deferred TTS families (Qwen3 CustomVoice, VibeVoice, MioTTS, VoxCPM2, PocketTTS) — by calling the raw audiocpp_server engines directly or spawning a private engine in the sandbox. Use when the user asks for a voice, model, or audio scenario the built-in audio tools reject or cannot express, including diarizing a meeting recording or labeling speakers in a transcript.

2026-07-2046

audiocpp-tts-controls

Elumenotion/GuideAnts

Advanced synthesis controls on the loaded audio.cpp TTS model: deterministic output via seed, forcing the spoken language, voice-design from a text description (instructions), and enumerating builtin speaker ids — none of which the built-in GuideAnts audio tools expose. Use when the user wants reproducible audio, a specific language, a described voice, or a list of available speakers.

2026-07-2046

name	audiocpp-voice-clone
description	Clone a voice from a user-supplied reference clip and synthesize speech with it, by calling the raw audio.cpp TTS engine with voice_ref/reference_text — fields the built-in GuideAnts audio tools do not expose. Use when the user wants generated speech to sound like their own voice or another consenting speaker's recording.
metadata	{"guideants":{"enabled":true,"display_order":31,"requires_toolsets":["sandbox"]}}

audio.cpp voice cloning (experimental)

Consent rule (read first)

Preflight

python3 Output/Skills/audiocpp-voice-clone/scripts/preflight.py --for voice-clone

Cloning

The reference clip must be a file in the workspace (e.g. an upload under Output/uploads/). Same container filesystem, so the engine reads it by path:

python3 Output/Skills/audiocpp-voice-clone/scripts/engine_tool.py speech \
  "Text to speak in the cloned voice" \
  -o Output/cloned.wav \
  --voice-ref Output/uploads/user_voice.wav \
  [--reference-text "transcript of the reference clip"] \
  [--seed 42]

The engine model id is auto-detected from the wrapper's /health (catalogEntryId); no flag needed.
--reference-text helps families that want the reference transcript.
--seed makes the synthesis reproducible.
The engine errors loudly on options the loaded family doesn't support — surface that error text to the user; it is usually self-explanatory.

Verifying

Transcribe the result back and check it matches the input text (the ASR engine at 127.0.0.1:18082 accepts workspace paths):

python3 Output/Skills/audiocpp-voice-clone/scripts/engine_tool.py transcribe Output/cloned.wav

When this skill isn't enough

Loaded model rejects voice_ref → ask the user to load chatterbox via Settings, or use the audiocpp-deferred-tts skill (several deferred families also clone from reference audio).
No TTS model loaded at all and the user can't load one → blocked; say so.

Reporting

End by telling the user what worked and what was blocked, quoting the preflight/engine evidence, so the experiment log stays honest.