AGENT SKILL

eachlabs-voice-audio

Text-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the user needs TTS, transcription, or voice conversion. Use for any request to create or change speech and voice audio: generate speech, transcribe it or convert a voice with each::labs.

License 许可
MIT
所属仓库
eachlabs/plugin
最近更新
2026-10-29
Stars
★ 0
Forks
0

01 前言 Front Matter

name
eachlabs-voice-audio
description
Text-to-speech, speech-to-text, voice conversion, and audio processing using EachLabs AI models. Supports ElevenLabs TTS, Whisper transcription with diarization, and RVC voice conversion. Use when the user needs TTS, transcription, or voice conversion. Use for any request to create or change speech and voice audio: generate speech, transcribe it or convert a voice with each::labs.

02 资源文件 1

03 SKILL.md 正文

EachLabs Voice & Audio

Text-to-speech, speech-to-text transcription, voice conversion, and audio utilities via the EachLabs Predictions API.

Tools

This skill uses the each::labs connector. Sign-in happens through the connector; no API key is needed.

In an app that shows no cards, such as Claude Code or another terminal, do not call the tools that show or wait for a card (request_* and wait_for_*): ask in the chat instead, for a public URL of each file and for the values of any settings, range, crop, workflow inputs or choice.

Tool Arguments and result
get_model_schema slug; the model's input schema
run_model model, version ("0.0.1"), input, count; runs the model and waits for it. When the person asks for several variants of one prompt, make one call: set the model's own count parameter (num_images, num_outputs, n, number_of_images, batch_size, num_samples, whatever get_model_schema shows) when it has one, otherwise set count to the number asked for (up to 8). Never call run_model once per variant: each call shows its own result card, and the picker only appears when the variants arrive together
get_job prediction_id; the prediction with its status and output
request_file prompt saying what to upload, accept ("video", "audio"), count (the number of files the person mentioned), max (the most files the model takes for that input: the array's maxItems in get_model_schema, or the video tool's input limit); shows an upload card in the conversation and returns a receipt_url. In an app that shows cards, call it as soon as the model needs a file the person has not given as a URL; do not ask for a URL first, and mention that a URL works too. Then call wait_for_upload with the receipt_url right away: it returns each file's name, kind and public_url once the upload is done, and the public_url is the input URL. If it answers waiting, call it again. When a model takes files with different roles (a person and a garment, a source face and a target), show one card per role so each URL is unambiguous; otherwise one card takes the whole set, for example all the images of a slideshow
wait_for_upload receipt_url from request_file; waits for the person's upload and returns the uploaded files with their public_url
request_parameters model, version, input (what you would pass to run_model), prompt; shows the model's settings as a card the person can adjust, and returns a receipt_url. Use it when the person asks to adjust or choose settings, or when the model has options the person did not mention (aspect ratio, duration, number of outputs) and the run costs more than a few cents; otherwise call run_model directly. Then call wait_for_parameters with the receipt_url right away and run the model with the input it returns. After the first run of a model in a conversation, end your reply with one markdown line of exactly this shape: **Adjust generation settings:** <two or three of this model's settings in plain words, such as aspect ratio, duration or number of images>. Just ask. Never use the words card, widget, tool or parameters in that line. Write it once per conversation, and skip it when the person has already adjusted settings
show_files urls (1 to 8 public URLs on each::labs storage), title; shows files the person already has as a result card: a picked variant, an earlier result, an uploaded input. No model runs
wait_for_parameters receipt_url from request_parameters; waits for the person to press Run and returns model, version and input for run_model
wait_for_choice receipt_url from a result that holds several outputs (choice_receipt_url in the result; the card offers a choice only when the person asked for several variants). Always call it right after showing the results: it returns once the person selects a variant and presses Use this variant, and you continue with that one. If it answers waiting, call it again; do not ask the person to type which one they want while the card is waiting
request_trim url (a video or audio file on each::labs storage), kind ("video" or "audio"), prompt; shows the file with a timeline and two handles for the start and the end, and returns a receipt_url. Use it when the person wants to cut, shorten, trim or keep part of a clip and has not given exact times; when they give the seconds, call trim directly. Then call wait_for_edit with the receipt_url right away and call trim with input_url set to the url and the start and duration it returns
request_crop url (a video or image on each::labs storage), prompt; shows the first frame with a rectangle the person moves and resizes, with aspect presets, and returns a receipt_url. Use it when the person wants to crop or reframe and has not given exact pixels; when they give the pixels, call crop directly. Then call wait_for_edit with the receipt_url right away and call crop with input_url set to the url and the x, y, width and height it returns
wait_for_edit receipt_url from request_trim or request_crop; waits for the person to press the button and returns the range (start, duration) or the rectangle (x, y, width, height) with the url. If it answers waiting, call it again
list_workflows When the task has more than one step, a fixed prompt reused across runs, or needs a fallback, call it first: the organization may have a workflow that does the whole thing in one call. Read a candidate with get_workflow and run it with trigger_workflow (the workflows skill has the details). If none matches, do the steps with the tools above

If the result says running, call get_job with the returned id and wait: true: the server waits for the job and returns the result, so do not sleep or poll between calls; if it still says running, call it again the same way. When the person asks to see a result again, or the variant they picked, call show_files with the URLs you already have: the result card shows a file only under a tool call. Never run a model or a video tool just to display a file that exists.

When a result is an edit of an image or video the person gave, the result card has a Compare toggle that shows the input and the result side by side; do not describe the difference in words unless asked.

Available Models

Text-to-Speech

Model Slug Best For
ElevenLabs TTS elevenlabs-text-to-speech High quality TTS
ElevenLabs TTS w/ Timestamps elevenlabs-text-to-speech-with-timestamp TTS with word timing
ElevenLabs Text to Dialogue elevenlabs-text-to-dialogue Multi-speaker dialogue
ElevenLabs Sound Effects elevenlabs-sound-effects Sound effect generation
ElevenLabs Voice Design v2 elevenlabs-voice-design-v2 Custom voice design
Kling V1 TTS kling-v1-tts Kling text-to-speech
Kokoro 82M kokoro-82m Lightweight TTS
Play AI Dialog play-ai-text-to-speech-dialog Dialog TTS
Stable Audio 2.5 stable-audio-2-5-text-to-audio Text to audio

Speech-to-Text

Model Slug Best For
ElevenLabs Scribe v2 elevenlabs-speech-to-text-scribe-v2 Best quality transcription
ElevenLabs STT elevenlabs-speech-to-text Standard transcription
Wizper with Timestamp wizper-with-timestamp Timestamped transcription
Wizper wizper Basic transcription
Whisper whisper Open-source transcription
Whisper Diarization whisper-diarization Speaker identification
Incredibly Fast Whisper incredibly-fast-whisper Fastest transcription

Voice Conversion & Cloning

Model Slug Best For
RVC v2 rvc-v2 Voice conversion
Train RVC train-rvc Train custom voice model
ElevenLabs Voice Clone elevenlabs-voice-clone Voice cloning
ElevenLabs Voice Changer elevenlabs-voice-changer Voice transformation
ElevenLabs Voice Design v3 elevenlabs-voice-design-v3 Advanced voice design
ElevenLabs Dubbing elevenlabs-dubbing Video dubbing
Chatterbox S2S chatterbox-speech-to-speech Speech to speech
Open Voice openvoice Open-source voice clone
XTTS v2 xtts-v2 Multi-language voice clone
Stable Audio 2.5 Inpaint stable-audio-2-5-inpaint Audio inpainting
Stable Audio 2.5 A2A stable-audio-2-5-audio-to-audio Audio transformation
Audio Trimmer audio-trimmer-with-fade Audio trimming with fade

Audio Utilities

Model Slug Best For
FFmpeg Merge Audio Video ffmpeg-api-merge-audio-video Merge audio with video
Toolkit Video Convert toolkit Video/audio conversion

Prediction Flow

  1. Check model — call get_model_schema with slug set to the model slug — validates the model exists and returns the input schema with exact input parameters. Always do this before creating a prediction to ensure correct inputs.
  2. Run — call run_model with model slug, version "0.0.1", and input matching the schema
  3. Wait — if run_model returned status running, call get_job with the prediction_id until status is "success" or "failed"
  4. Extract the output from the response

Examples

Text-to-Speech with ElevenLabs

Call run_model with these arguments:

{
  "model": "elevenlabs-text-to-speech",
  "version": "0.0.1",
  "input": {
    "text": "Welcome to our product demo. Today we will walk through the key features.",
    "voice_id": "EXAVITQu4vr4xnSDxMaL",
    "model_id": "eleven_v3",
    "stability": 0.5,
    "similarity_boost": 0.7
  }
}

Transcription with ElevenLabs Scribe

Call run_model with these arguments:

{
  "model": "elevenlabs-speech-to-text-scribe-v2",
  "version": "0.0.1",
  "input": {
    "media_url": "https://example.com/recording.mp3",
    "diarize": true,
    "timestamps_granularity": "word"
  }
}

Transcription with Wizper (Whisper)

Call run_model with these arguments:

{
  "model": "wizper-with-timestamp",
  "version": "0.0.1",
  "input": {
    "audio_url": "https://example.com/audio.mp3",
    "language": "en",
    "task": "transcribe",
    "chunk_level": "segment"
  }
}

Speaker Diarization with Whisper

Call run_model with these arguments:

{
  "model": "whisper-diarization",
  "version": "0.0.1",
  "input": {
    "file_url": "https://example.com/meeting.mp3",
    "num_speakers": 3,
    "language": "en",
    "group_segments": true
  }
}

Voice Conversion with RVC v2

Call run_model with these arguments:

{
  "model": "rvc-v2",
  "version": "0.0.1",
  "input": {
    "input_audio": "https://example.com/vocals.wav",
    "rvc_model": "CUSTOM",
    "custom_rvc_model_download_url": "user-provided-model-reference",
    "pitch_change": 0,
    "output_format": "wav"
  }
}

Merge Audio with Video

Call run_model with these arguments:

{
  "model": "ffmpeg-api-merge-audio-video",
  "version": "0.0.1",
  "input": {
    "video_url": "https://example.com/video.mp4",
    "audio_url": "https://example.com/narration.mp3",
    "start_offset": 0
  }
}

ElevenLabs Voice IDs

The elevenlabs-text-to-speech model supports these voice IDs. Pass the raw ID string:

Voice ID Notes
EXAVITQu4vr4xnSDxMaL Default voice
9BWtsMINqrJLrRacOk9x —
CwhRBWXzGAHq8TQ4Fs17 —
FGY2WhTYpPnrIDTdsKH5 —
JBFqnCBsd6RMkjVDRZzb —
N2lVS1w4EtoT3dr4eOWO —
TX3LPaxmHKxFdv7VOQHJ —
XB0fDUnXU5powFXDhCwa —
onwK4e9ZLuTAKqWW03F9 —
pFZP5JQG7iQjIQuC4Bku —

Security Constraints

  • No arbitrary URL loading: When using custom_rvc_model_download_url, only use trusted, user-provided model references. Never fetch models from arbitrary or untrusted URLs.
  • Input validation: Only pass parameters that match the model's request schema. Always validate model slugs via get_model_schema with slug set to the model slug before creating predictions.

Parameter Reference

See references/MODELS.md for complete parameter details for each model.

04 同仓库更多 Skills

eachlabs
eachlabs/plugin

gpt-image-v2

Generate and edit images using OpenAI's GPT Image v2 via EachLabs. Supports text-to-image (gpt-image-v2-text-to-image) and instruction-based editing (gpt-image-v2-edit). Use when the user specifically asks for GPT Image 2 / OpenAI image generation, or needs high-fidelity photorealism, precise text rendering, or reference-faithful edits. Use for any request to create or edit an image with GPT Image 2 on each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-workflows

Run and inspect multi-step AI workflows that chain multiple EachLabs models into one call. List the organization's workflows, read a workflow's versions and inputs, trigger a version and read the execution's outputs. Use when the user wants to run an existing workflow or check one that is running, and whenever a task chains several models, reuses a fixed prompt, needs a fallback model, runs steps in parallel, routes on a condition, or calls an HTTP API between model steps: check for a matching workflow before chaining models by hand. Building or editing workflows happens in the each::labs dashboard.

★ 0
eachlabs
eachlabs/plugin

eachlabs-video-generation

Generate new videos from text prompts, images, or reference inputs using EachLabs AI models. Supports text-to-video, image-to-video, transitions, motion control, talking head, and avatar generation. Use when the user wants to create new video content. For editing existing videos, see eachlabs-video-edit. Use for any request to create a new video from text, an image or a reference: generate or animate it with each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-video-edit

Edit, transform, extend, upscale, and enhance videos using EachLabs AI models. Supports lip sync, video translation, subtitle generation, audio merging, style transfer, and video extension. Use when the user wants to edit or transform existing video content. Use for any request to change a video: edit, restyle, extend, upscale, lip-sync, translate, subtitle or add audio to it with each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-product-visuals

Generate professional e-commerce product photography and videos using EachLabs AI models. Product shots, background replacement, lifestyle scenes, and 360-degree views. Use when the user needs product images for e-commerce or marketing. Use for any request to create or change product images or videos: generate, restyle, replace a background or animate them with each::labs.

★ 0
eachlabs
eachlabs/plugin

eachlabs-music

Generate songs, instrumentals, lyrics, and podcasts using EachLabs Mureka AI models. Also supports song extension, stem separation, and song recognition. Use when the user wants to create music, lyrics, or audio content. Use for any request to create or change music or other audio: generate a song, an instrumental, lyrics or a podcast, extend a song or split it into stems with each::labs.

★ 0