GET
/v1/schemas/fal/audio/fal-ai/elevenlabs/tts/eleven-v3
Accept:
| field | recorded source |
|---|---|
| schema | Source linked above. upstream-spec Source trace985ccff46488f3cbe84fc690291c23f6c6ff33b8fa52afc138eda8cf6563b166{
"fetchedAt": 1794459602,
"extractorVersion": "2",
"verifiedAt": null
} |
Request body
8 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| text* | string | The text to convert to speech | length ≥ 1 · length ≤ 5000 |
| enable_safety_checker | boolean | Check input content for safety. Disabling requires account authorization. | default: true |
| timestamps | boolean | Whether to return timestamps for each word in the generated speech | default: false |
| output_format | enum | Output audio format (codec_sample_rate_bitrate). PCM is raw signed 16-bit little-endian audio, without a WAV header. PCM at 44.1 kHz requires an ElevenLabs Pro plan or above; MP3 at 192 kbps requires Creator or above. | mp3_22050_32 | mp3_44100_32 | mp3_44100_64 | mp3_44100_96 | mp3_44100_128 | mp3_44100_192 · +13 more · default: "mp3_44100_128" |
| language_code | string | Language code (ISO 639-1) used to enforce a language for the model. | nullable |
| apply_text_normalization | 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 applie… | auto | on | off · default: "auto" |
| voice | string | The voice to use for speech generation | default: "Rachel" |
| stability | number | Voice stability (0-1) | 0 ≤ n ≤ 1 · default: 0.5 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/elevenlabs/tts/eleven-v3","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}