ElevenLabs offers 20 models through Lava’s AI Gateway, supporting Text to Speech, Text to Speech (Streaming), Speech to Text. Authentication uses xi-api-key. See the ElevenLabs API docs for provider-specific parameters.
Supports both managed API keys (from Lava) and BYOK mode.
Quick Start
const response = await fetch('https://api.lavapayments.com/v1/forward?u=https%3A%2F%2Fapi.elevenlabs.io%2Fv1%2Ftext-to-speech%2Feleven_ttv_v3', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'xi-api-key': forwardToken,
},
body: JSON.stringify({
text: "Hello, world!",
}),
});
Text to Speech
Target URL: https://api.elevenlabs.io/v1/text-to-speech/{voice_id}
| |
|---|
| Content Type | application/json |
| Streaming | No |
| Model | Input / 1M chars | Output / 1M chars |
|---|
| eleven_ttv_v3 | $2.40 | $2.40 |
| eleven_multilingual_v2 | $2.40 | $2.40 |
| eleven_multilingual_ttv_v2 | $2.40 | $2.40 |
| eleven_monolingual_v1 | $2.40 | $2.40 |
| eleven_multilingual_v1 | $2.40 | $2.40 |
| eleven_flash_v2_5 | $1.20 | $1.20 |
| eleven_flash_v2 | $1.20 | $1.20 |
| eleven_turbo_v2_5 | $1.20 | $1.20 |
| eleven_turbo_v2 | $1.20 | $1.20 |
Text to Speech (Streaming)
Target URL: https://api.elevenlabs.io/v1/text-to-speech/stream/{voice_id}
| |
|---|
| Content Type | application/json |
| Streaming | No |
| Model | Input / 1M chars | Output / 1M chars |
|---|
| eleven_ttv_v3 | $2.40 | $2.40 |
| eleven_multilingual_v2 | $2.40 | $2.40 |
| eleven_multilingual_ttv_v2 | $2.40 | $2.40 |
| eleven_monolingual_v1 | $2.40 | $2.40 |
| eleven_multilingual_v1 | $2.40 | $2.40 |
| eleven_flash_v2_5 | $1.20 | $1.20 |
| eleven_flash_v2 | $1.20 | $1.20 |
| eleven_turbo_v2_5 | $1.20 | $1.20 |
| eleven_turbo_v2 | $1.20 | $1.20 |
Speech to Text
Target URL: https://api.elevenlabs.io/v1/speech-to-text
| |
|---|
| Content Type | multipart/form-data |
| Streaming | No |
| Model | Input / minute | Output / minute |
|---|
| scribe_v1 | $0.0067 | Free |
| scribe_v1_experimental | $0.0067 | Free |
Next Steps
