GET
/v1/schemas/fal/audio/fal-ai%2Fbytedance%2Fseed-speech%2Ftts%2Fv2
Accept:
Request body
9 properties · 1 required · 0 $defs| property | type | description | constraints |
|---|---|---|---|
| text* | string | The text to synthesize into speech. | length ≤ 5000 |
| output_format | enum | Output audio format. 'mp3' returns MP3 audio; 'opus' returns Opus audio in an Ogg container. | mp3 | opus · default: "mp3" |
| sample_rate | enum | Sample rate of the output audio in Hz. | 8000 | 16000 | 22050 | 24000 | 32000 | 44100 · +1 more · default: 24000 |
| volume | number | Volume. 1.0 is normal volume, 0.5 is half, 2.0 is double. | 0.5 ≤ n ≤ 2 · default: 1 |
| pitch | integer | Voice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave. | -12 ≤ n ≤ 12 · default: 0 |
| language | enum | Force the text to be read as a single language, disabling automatic language detection. Leave unset for automatic detection (including seamless Chinese/English mixing on bilingual voices). Codes: zh (Chinese), en (English), ja (Japanese), es-mx (Mexican Spanish), id (Indonesian), pt-br (Brazilian Portuguese), ko (Korean), it (Italian), de (German), fr (French). | zh | en | ja | es-mx | id | pt-br · +4 more · nullable |
| voice | enum | Voice to use for synthesis. The preset name encodes the voice and its supported language codes. 'mixed_en_zh' means the voice can seamlessly blend English and Chinese; separate codes (e.g. 'en_zh') mean the voice supports each language independently. | vivi_mixed_en_zh_ja_es_id | mindy_en_es_id_pt_zh | stokie_en | dacey_en | tim_en | kian_en_zh · +35 more · default: "stokie_en" |
| voice_instruction | string | Optional natural-language instruction that steers the delivery (tone, emotion, pace, volume), e.g. 'Speak in a cheerful tone' or 'Could you speak a bit slower?'. It is not spoken aloud and does not affect billing. | nullable |
| speed | number | Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed. | 0.5 ≤ n ≤ 2 · default: 1 |
Validate a payload
before you spend tokensshell
$ curl -X POST https://modelschemas.com/v1/validate \
-d '{"provider":"fal","endpointId":"fal-ai/bytedance/seed-speech/tts/v2","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}