ElevenLabs TTS v3
Text to audio
Starting price $0.17 / run
By ElevenLabs
ElevenLabs TTS Multilingual v2 reads your text aloud in a natural voice, in many languages, with controls for stability, style and speed.
elevenlabs/tts/multilingual-v2Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.
# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "elevenlabs/tts/multilingual-v2",
"input": {
"text": "Meet the new trail backpack: light enough for a day hike, roomy enough for a weekend away."
}
}'
# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
-H "Authorization: Bearer $RAYWAKE_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"model": "elevenlabs/tts/multilingual-v2", "quote_id": "QUOTE_ID", "input": {"text":"Meet the new trail backpack: light enough for a day hike, roomy enough for a weekend away."}}'
# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAYWAKE_API_KEY"| Name | Type | Description |
|---|---|---|
textrequired | string | The text to convert to speech |
voice | string | The voice to use for speech generation |
stability | number | Voice stability (0-1) |
similarity_boost | number | Similarity boost (0-1) |
style | number | Style exaggeration (0-1) |
speed | number | Speech speed (0.7-1.2). Values below 1.0 slow down the speech, above 1.0 speed it up. Extreme values may affect quality. |
timestamps | boolean | Whether to return timestamps for each word in the generated speech |
language_code | string | Language code (ISO 639-1) used to enforce a language for the model. An error will be returned if language code is not supported by the model. |
apply_text_normalization | string (enum) | This parameter controls text normalization with three modes: 'auto', 'on', and 'off'. When set to 'auto', the system will automatically decide whether to apply text normalization (e.g., spelling out numbers). With 'on', text normalization will always be applied, while with 'off', it will be skipped. |
A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.
"outputs": [
{ "type": "audio", "url": "https://…", "mime_type": "audio/mpeg", "thumbnail_url": null }
]The exact charge for your input comes from a quote. How charges settle
Fields marked * are required. Review the price before generating.
ElevenLabs TTS Multilingual v2 turns written text into speech. Pick a voice, set how steady or expressive it sounds, and slow it down or speed it up within a narrow range.
It can return a timestamp for every word, which helps with subtitles and lip sync, and you can fix the language when the text could be read as more than one.
Listen for accents, proper names and numbers in the requested language. Check the whole recording before using timestamps for subtitles.