VARIANTE · ElevenLabs / ElevenLabs

ElevenLabs speech-to-text API

A model variant exposed through RunAPI's unified AI API.

Operational · audio_music · Commercial use supported
# Works with Claude Code, Codex, Gemini CLI, Cursor, and 50+ agents
npx skills add runapi-ai/elevenlabs -g
The -g flag installs globally so every project picks it up.
Or paste this prompt to your AI agent:
Install the ElevenLabs skill for me:

1. Clone https://github.com/runapi-ai/elevenlabs
2. Copy the skills/elevenlabs/ directory into your
   user-level skills directory (e.g. ~/.claude/skills/
   for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
Switch variant
RESUMEN

ElevenLabs speech-to-text is available through the same RunAPI auth, SDKs, and agent skill workflow.

  • Unified endpoint
  • SDK snippets
  • Agent install path
  • Las generaciones fallidas no se cobran
PRECIOS

PRECIOS

Las generaciones fallidas no se cobran
Speech to text
$0.04 / minute
FICHA TÉCNICA

FICHA TÉCNICA

Model ID speech-to-text
Proveedor ElevenLabs
Modalidad audio_music
Task type asynchronous
Facturación minute
Endpoint /api/v1/elevenlabs/speech_to_text
Commercial Yes
Status Operational
INICIO RÁPIDO

Quickstart — speech-to-text

runapi.ai
curl -X POST https://runapi.ai/api/v1/elevenlabs/speech_to_text \
  -H "Authorization: Bearer $RUNAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "speech-to-text",
  "audio_url": "https://cdn.runapi.ai/public/samples/voice.mp3"
}'
import { ElevenlabsClient } from "@runapi.ai/elevenlabs";

const client = new ElevenlabsClient();
const result = await client.speechToText.run({
    model: "speech-to-text",
    audio_url: "https://cdn.runapi.ai/public/samples/voice.mp3",
});
require "runapi/elevenlabs"

client = RunApi::Elevenlabs::Client.new
result = client.speech_to_text.run(
    model: "speech-to-text",
    audio_url: "https://cdn.runapi.ai/public/samples/voice.mp3"
)
@runapi.ai/elevenlabs v1
CÓMO FUNCIONA

How to use speech-to-text

01

Choose endpoint

Pick the endpoint and copy the SDK snippet.

02

Pass model ID

Use this variant ID in the request body.

03

Run task

Submit the request and store the returned task ID.

04

Collect output

Poll or receive the callback when the task finishes.

DIFERENCIAS

How speech-to-text compares

VS AUDIO-ISOLATION

Transcription across 29+ languages with speaker diarization

Vocal extraction from mixed audio sources

VS SOUND-EFFECT-V2

Transcription across 29+ languages with speaker diarization

Text-to-sound effects for games, video, and podcasts

VS TEXT-TO-DIALOGUE-V3

Transcription across 29+ languages with speaker diarization

Multi-speaker dialogue generation with natural turn-taking

CASOS DE USO

Where to use this variant

Music generation

Create tracks and audio assets.

Voice workflows

Build speech and audio pipelines.

Agent creation

Expose audio tools to agents.

FAQ

Frequently asked questions about speech-to-text

How do I select speech-to-text?

Pass the model ID shown in the quickstart.

Is pricing usage-based?

Yes. Pricing is metered per call or unit.

EMPEZAR

Start with ElevenLabs today.