ElevenLabs · Audio & Music
OpenClaw x ElevenLabs
ElevenLabs is a voice AI company whose models cover TTS, dialogue, sound effects, transcription, and audio isolation. Through RunAPI, all ElevenLabs endpoints share one key and per-call billing.
Public versions and endpoints
| Model ID | Version | Endpoints | Starting price | Catalog |
|---|---|---|---|---|
audio-isolation | Vocal extraction from mixed audio sources | /api/v1/elevenlabs/isolate_audio | $0.120 | Model detail |
sound-effect-v2 | Text-to-sound effects for games, video, and podcasts | /api/v1/elevenlabs/text_to_sound | $0.150 | Model detail |
speech-to-text | Transcription across 29+ languages with speaker diarization | /api/v1/elevenlabs/speech_to_text | $0.040 | Model detail |
text-to-dialogue-v3 | Multi-speaker dialogue generation with natural turn-taking | /api/v1/elevenlabs/text_to_dialogue | $0.140 | Model detail |
text-to-speech-multilingual-v2 | 29 languages; most lifelike emotional expression; ideal for audiobooks | /api/v1/elevenlabs/text_to_speech | $0.120 | Model detail |
text-to-speech-turbo-v2.5 | 32 languages; 3× faster non-English; 40K char limit; cheapest | /api/v1/elevenlabs/text_to_speech | $0.060 | Model detail |
Configuration
Guide endpoint: <endpoint>
Select <model-id> to generate a request with the endpoint's public input contract.Verify
Select <model-id> to generate verification commands.How it works
- 1. Choose a model ID
Select a public catalog model ID and review its endpoint and current starting price.
- 2. Configure RunAPI
Set RUNAPI_API_KEY before making the endpoint request.
- 3. Verify the result
For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.
FAQ
Which model ID should I use?
Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.
Does this guide configure a chat model?
No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.