← All models
Seed Speech developed by ByteDance, is a family of large-scale text-to-speech models capable of synthesizing speech that is virtually indistinguishable from human speech.
Details
- Accepts
- text
Pricing
- Price
- 0.00375 cr / character
Prices in credits (1 credit = $0.01).
Data schema
Input
| Field | Type | Description |
|---|---|---|
| textrequired | string | The text to synthesize into speech. |
| pitch | integer | Voice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave. |
| speed | number | Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed. |
| voice | stringenum: vivi_mixed_en_zh_ja_es_id, mindy_en_es_id_pt_zh, stokie_en, dacey_en, tim_en, kian_en_zh… | 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. |
| volume | number | Volume. 1.0 is normal volume, 0.5 is half, 2.0 is double. |
| language | — | 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 Po… |
| sample_rate | integerenum: 8000, 16000, 22050, 24000, 32000, 44100… | Sample rate of the output audio in Hz. |
| output_format | stringenum: mp3, opus | Output audio format. 'mp3' returns MP3 audio; 'opus' returns Opus audio in an Ogg container. |
| voice_instruction | — | 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. |
Output
| Field | Type | Description |
|---|---|---|
| audio | — | The generated audio file. |