Start building

Bytedance Seed Speech Text to Speech

bytedance/seed-speech/tts/2.0

Seed Speech Tts 2.0 is Bytedance's text-to-speech AI model. Generate human-like voiceovers with expressive intonation, multilingual support, and customizable voice characteristics.

Use in agentGet API key
Base price
$0.06USD / run
Execution
async
Model type
audio
Input fields
9
Production route

Try the model

Playground

Open playground
Input
The text to synthesize into speech.
Output audio format. 'mp3' returns MP3 audio; 'opus' returns Opus audio in an Ogg container. Allowed values: mp3, opus.
Sample rate of the output audio in Hz. Allowed values: 8000, 16000, 22050, 24000, 32000, 44100, 48000.
0.52
Volume. 1.0 is normal volume, 0.5 is half, 2.0 is double. Range: 0.5 to 2.
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. Allowed values: vivi_mixed_en_zh_ja_es_id, mindy_en_es_id_pt_zh, stokie_en, dacey_en, tim_en, kian_en_zh, cedric_en_zh, sophie_en_zh, jean_en_zh, magnus_en_zh, mabel_en_zh, nadia_en_zh, opal_en_zh, pearl_en_zh, quentin_en_zh, vienna_mixed_en_zh, alina_mixed_en_zh, corinne_mixed_en_zh, esther_mixed_en_zh, freya_mixed_en_zh, gigi_mixed_en_zh, holly_mixed_en_zh, lyla_mixed_en_zh, daisy_mixed_en_zh, tracy_es_zh, jess_ja_es_id_pt_en_zh, pinky_es_ko_mixed_en_zh, sweety_ja_es, sandy_es_mixed_en_zh, sven_de, minimi_ja, usseau_fr, felipe_es, han_id, martins_pt, enzo_it, shane_ko, bonnie_zh, felix_zh, celeste_zh, monkey_king_zh.
-1212
Voice pitch shift in semitones. 0 is normal pitch, -12 lowers by one octave, 12 raises by one octave. Range: -12 to 12.
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). Allowed values: zh, en, ja, es-mx, id, pt-br, ko, it, de, fr.
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.
0.52
Speech speed. 1.0 is normal speed, 0.5 is half speed, 2.0 is double speed. Range: 0.5 to 2.
OutputExample

  1. What would you like to do next?

    Open original

Examples

Select an example to load its inputs and result into the playground.

Model card

Specifications

Pricing

Base price
$0.06 / run

Context & modalities

Input
Schema-defined
Output
audio

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
ByteDance
Model ID
bytedance/seed-speech/tts/2.0
Execution
async
Base URL
https://api.sandbase.ai
API
Unified Run API
Endpoint
/v1/run

API README

Bytedance Seed Speech Text to Speech

Seed Speech TTS 2.0 generates expressive, multilingual voiceovers in 10 languages, with pitch, speed, and volume control and a free-text voice_instruction for delivery.

Fields

FieldTypeDefaultNotes
textstring—Text to speak.
output_formatmp3 / opusmp3Output file format.
sample_rate8000 / 16000 / 22050 / 24000 / 32000 / 44100 / 4800024000Output sample rate in Hz.
volumenumber 0.5–210.5–2× loudness.
voicevivi_mixed_en_zh_ja_es_id / mindy_en_es_id_pt_zh / stokie_en / dacey_en / tim_en / kian_en_zh / cedric_en_zh / sophie_en_zh / jean_en_zh / magnus_en_zh / mabel_en_zh / nadia_en_zh / opal_en_zh / pearl_en_zh / quentin_en_zh / vienna_mixed_en_zh / alina_mixed_en_zh / corinne_mixed_en_zh / esther_mixed_en_zh / freya_mixed_en_zh / gigi_mixed_en_zh / holly_mixed_en_zh / lyla_mixed_en_zh / daisy_mixed_en_zh / tracy_es_zh / jess_ja_es_id_pt_en_zh / pinky_es_ko_mixed_en_zh / sweety_ja_es / sandy_es_mixed_en_zh / sven_de / minimi_ja / usseau_fr / felipe_es / han_id / martins_pt / enzo_it / shane_ko / bonnie_zh / felix_zh / celeste_zh / monkey_king_zhstokie_enPreset voice; names list the languages each voice supports.
pitchinteger -12–120Semitones, −12 to 12.
languagezh / en / ja / es-mx / id / pt-br / ko / it / de / fr—Force the text to be read as a single language, disabling automatic language detection.
voice_instructionstring—How to say it, e.g. “excited sports commentator”.
speednumber 0.5–210.5–2× speaking rate.

Billing

$0.06 per started 1,000 characters of text, with a one-unit minimum.

TextPrice
200 characters$0.06
1,000 characters$0.06
2,500 characters$0.18

Failed runs are not charged.

Prompting

  • Pick a voice whose language list includes the text's language.

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
bytedance/seed-speech/tts/2.0
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "bytedance/seed-speech/tts/2.0",
  "text": "Hello, this is a test of ByteDance TTS 2.0 speech synthesis.",
  "pitch": 0,
  "speed": 1,
  "voice": "stokie_en",
  "volume": 1,
  "sample_rate": 24000,
  "output_format": "mp3",
  "voice_instruction": "Speak in a warm, cheerful tone."
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All image & video models
ModelTypeDefault priceReleased
Bytedance Seed Speech Text to SpeechThis model
ByteDance		Audio$0.06 / runJun 5, 2026
ByteDance OmniHuman 2.0
ByteDance		Video$0.53 / runOct 15, 2026
Seed-2.1-Pro
ByteDance		llm—Sep 16, 2026
Seedream 5.0 Flash Text to Image
ByteDance		Image$0.02 / runSep 15, 2026
Seedream 5.0 Flash Edit
ByteDance		Image$0.02 / runSep 15, 2026
Seedream 5.0 Pro Edit
ByteDance		Image$0.09 / runJul 8, 2026

Questions

FAQ

How do I call Bytedance Seed Speech Text to Speech through SandBase?

Create a SandBase API key, then send requests with the model ID "bytedance/seed-speech/tts/2.0" to Unified Run API (/v1/run) at https://api.sandbase.ai. The request examples on this page show the exact payload.

Do I need a separate ByteDance account?

No. One SandBase API key and balance gives you access to Bytedance Seed Speech Text to Speech and the other models in the catalog; you do not need to sign up with ByteDance separately.