ElevenLabs | Text to Speech with Timestamp
Convert text to speech using ElevenLabs' high-quality voices with word-level timestamp data. Supports multiple voices, models, languages, and fine-grained voice settings for stability, similarity, and speed.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "elevenlabs-text-to-speech-with-timestamp",
"version": "0.0.1",
"input": {
"text": "Welcome to our product demo. Today we will walk you through the key features.",
"voice_id": "9BWtsMINqrJLrRacOk9x",
"model_id": "eleven_multilingual_v2",
"stability": 0.5,
"similarity_boost": 0.7
}
}'
Parameters
| Parameter |
Type |
Default |
Description |
| apply_language_text_normalization |
boolean |
false |
Apply language-specific text normalization. |
| apply_text_normalization |
string |
auto |
Text normalization mode. Options: auto, on, off |
| language_code |
string |
- |
Language code (ISO 639-1) for language enforcement and text normalization. |
| model_id |
string |
eleven_multilingual_v2 |
ElevenLabs model. Options: eleven_multilingual_v2, eleven_flash_v2_5, eleven_turbo_v2_5, eleven_turbo_v2, eleven_flash_v2, eleven_monolingual_v1, eleven_multilingual_v1, eleven_v3 |
| next_text |
string |
- |
Text that comes after the current text for context. |
| previous_text |
string |
- |
Text that comes before the current text for context. |
| seed |
integer |
- |
Seed for reproducibility. |
| similarity_boost |
number |
0.7 |
Voice similarity boost (0-1). |
| speed |
number |
- |
Speech speed multiplier. |
| stability |
number |
0.5 |
Voice stability (0-1). Lower values are more expressive. |
| style |
number |
- |
Style exaggeration (0-1). |
| text |
string |
- |
The text to convert to speech. |
| use_speaker_boost |
boolean |
false |
Enable speaker boost for clearer voice. |
| voice_id |
string |
- |
ElevenLabs voice ID. Built-in voices include: Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill. |
Examples
Simple text-to-speech:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "elevenlabs-text-to-speech-with-timestamp",
"version": "0.0.1",
"input": {
"text": "Hello, this is a test of the text to speech system.",
"voice_id": "EXAVITQu4vr4xnSDxMaL"
}
}'
High-quality multilingual with custom settings:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "elevenlabs-text-to-speech-with-timestamp",
"version": "0.0.1",
"input": {
"text": "Bienvenue dans notre demonstration. Nous allons explorer les fonctionnalites principales.",
"voice_id": "FGY2WhTYpPnrIDTdsKH5",
"model_id": "eleven_multilingual_v2",
"language_code": "fr",
"stability": 0.6,
"similarity_boost": 0.8,
"use_speaker_boost": true,
"speed": 0.9
}
}'
Related Models
Documentation
1---2name: elevenlabs-text-to-speech-with-timestamp3description: ElevenLabs | Text to Speech with Timestamp. Convert text to speech with word-level timestamps using ElevenLabs voices. Triggers: text to speech, tts, elevenlabs, voice synthesis, timestamps4---56# ElevenLabs | Text to Speech with Timestamp78Convert text to speech using ElevenLabs' high-quality voices with word-level timestamp data. Supports multiple voices, models, languages, and fine-grained voice settings for stability, similarity, and speed.910## Quick Start1112> Requires an each::labs API key. Get one at [eachlabs.ai](https://eachlabs.ai).1314```bash15curl -X POST https://api.eachlabs.ai/v1/prediction \16 -H "Content-Type: application/json" \17 -H "X-API-Key: $EACHLABS_API_KEY" \18 -d '{19 "model": "elevenlabs-text-to-speech-with-timestamp",20 "version": "0.0.1",21 "input": {22 "text": "Welcome to our product demo. Today we will walk you through the key features.",23 "voice_id": "9BWtsMINqrJLrRacOk9x",24 "model_id": "eleven_multilingual_v2",25 "stability": 0.5,26 "similarity_boost": 0.727 }28 }'29```3031## Parameters3233| Parameter | Type | Default | Description |34|-----------|------|---------|-------------|35| apply_language_text_normalization | boolean | false | Apply language-specific text normalization. |36| apply_text_normalization | string | auto | Text normalization mode. Options: `auto`, `on`, `off` |37| language_code | string | - | Language code (ISO 639-1) for language enforcement and text normalization. |38| model_id | string | eleven_multilingual_v2 | ElevenLabs model. Options: `eleven_multilingual_v2`, `eleven_flash_v2_5`, `eleven_turbo_v2_5`, `eleven_turbo_v2`, `eleven_flash_v2`, `eleven_monolingual_v1`, `eleven_multilingual_v1`, `eleven_v3` |39| next_text | string | - | Text that comes after the current text for context. |40| previous_text | string | - | Text that comes before the current text for context. |41| seed | integer | - | Seed for reproducibility. |42| similarity_boost | number | 0.7 | Voice similarity boost (0-1). |43| speed | number | - | Speech speed multiplier. |44| stability | number | 0.5 | Voice stability (0-1). Lower values are more expressive. |45| style | number | - | Style exaggeration (0-1). |46| text | string | - | The text to convert to speech. |47| use_speaker_boost | boolean | false | Enable speaker boost for clearer voice. |48| voice_id | string | - | ElevenLabs voice ID. Built-in voices include: Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill. |4950## Examples5152**Simple text-to-speech:**53```bash54curl -X POST https://api.eachlabs.ai/v1/prediction \55 -H "Content-Type: application/json" \56 -H "X-API-Key: $EACHLABS_API_KEY" \57 -d '{58 "model": "elevenlabs-text-to-speech-with-timestamp",59 "version": "0.0.1",60 "input": {61 "text": "Hello, this is a test of the text to speech system.",62 "voice_id": "EXAVITQu4vr4xnSDxMaL"63 }64 }'65```6667**High-quality multilingual with custom settings:**68```bash69curl -X POST https://api.eachlabs.ai/v1/prediction \70 -H "Content-Type: application/json" \71 -H "X-API-Key: $EACHLABS_API_KEY" \72 -d '{73 "model": "elevenlabs-text-to-speech-with-timestamp",74 "version": "0.0.1",75 "input": {76 "text": "Bienvenue dans notre demonstration. Nous allons explorer les fonctionnalites principales.",77 "voice_id": "FGY2WhTYpPnrIDTdsKH5",78 "model_id": "eleven_multilingual_v2",79 "language_code": "fr",80 "stability": 0.6,81 "similarity_boost": 0.8,82 "use_speaker_boost": true,83 "speed": 0.984 }85 }'86```8788## Related Models8990- [ElevenLabs | Text to Speech](../elevenlabs-text-to-speech/) - Standard text to speech without timestamps91- [ElevenLabs | Voice Clone](../elevenlabs-voice-clone/) - Clone a voice from audio92- [ElevenLabs | Voice Design v3](../elevenlabs-voice-design-v3/) - Design custom voices9394## Documentation9596- [each::labs Docs](https://docs.eachlabs.ai)97- [API Reference](https://docs.eachlabs.ai/api/overview)
awesome-genmedia