Text to SpeechAbout Seed Speech 2.0
ByteDance's Seed Speech 2.0 text-to-speech, released in March 2026: send a script, pick one of 41 preset voices, describe the delivery in plain language and get back an MP3.
Call it with the model name bytedance/seed-speech-2.0/text-to-speech on POST /jobs/createTask, from 11 credits per 1,000 characters ($0.11). New accounts get 30 free credits to try it in the Playground first.
Introduction
What it returns
One audio file per task: a 24 kHz mono MP3 unless you set output_format or sample_rate. There are no word timings or subtitles in the result.
Choosing a voice
voice_id takes one of 41 preset voices and defaults to stokie_en. The suffix of each voice name lists the languages it is built for — tim_en is English, minimi_ja Japanese, sven_de German, jess_ja_es_id_pt_en_zh speaks several. Mixed voices keep the same timbre across their languages.
Directing the delivery
instructions takes a sentence or two of plain language about how to read: tone, emotion, pace, volume. It shapes the performance and is not spoken. For exact control, speed (0.5–2), pitch (-12 to 12 semitones) and volume (0.5–2) have their own sliders.
Output format
output_format picks mp3 (default) or opus, an Ogg Opus file that is smaller at the same quality, and sample_rate goes from 8000 to 48000 Hz.
Language
The language is detected from the script. language forces one of zh, en, ja, es-mx, id, pt-br, ko, it, de or fr when a short or mixed script is read in the wrong one.
Request parameters
| Parameter | Required | Description |
|---|---|---|
text | Yes | The words to be spoken, exactly as written. Billed per 1,000 characters. |
pitch | No | Pitch shift in semitones; 0 keeps the voice's own pitch. ≥ -12 · ≤ 12 · Default: 0 |
speed | No | Speaking pace. ≥ 0.5 · ≤ 2 · Default: 1 |
volume | No | Loudness multiplier; 1 is the normal level. ≥ 0.5 · ≤ 2 · Default: 1 |
language | No | The language of the speech. zh · en · ja · es-mx · id · pt-br · ko · it · de · fr |
voice_id | No | Pick from the available voices. 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 · Default: stokie_en |
sample_rate | No | Sample rate in Hz. The model uses 24000 when omitted. 8000–48000 |
instructions | No | How to read the text: tone, emotion, pace or volume. Not spoken and not billed. |
output_format | No | File type of the result. mp3 · opus · Default: mp3 |
Pricing
Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.
| Option | Credits per 1,000 characters | ≈ USD |
|---|---|---|
| Standard | 10.8 | $0.11 |
Each task is rounded up to whole credits, so one run at the lowest tier costs 11 credits per 1,000 characters ($0.11).
For an exact number before you run, send the same body to POST /jobs/quote.
API quick start
Call the Seed Speech 2.0 API in three steps
- Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
- Send the request. POST /jobs/createTask with model bytedance/seed-speech-2.0/text-to-speech and an input object that follows the parameter table. The response returns a task ID straight away.
- Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seed-speech-2.0/text-to-speech",
"input": {
"text": "Welcome back. Your files finished rendering a minute ago and are ready to download.",
"voice_id": "stokie_en",
"output_format": "mp3"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.
Seed Speech 2.0 API questions
How much does the Seed Speech 2.0 API cost?
Seed Speech 2.0 costs 11 credits ($0.11) per 1,000 characters. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.
What is the model name for Seed Speech 2.0 in the API?
Put bytedance/seed-speech-2.0/text-to-speech for Text to Speech in the model field of POST /jobs/createTask.
How do I control the delivery?
Pick one of 41 preset voices with voice_id and describe the delivery in instructions — tone, emotion, pace or volume, in a sentence or two. The instructions shape the reading and are not spoken aloud.
Which languages does it read?
It detects the language of the script automatically. You can also force Chinese, English, Japanese, Mexican Spanish, Indonesian, Brazilian Portuguese, Korean, Italian, German or French with language. Several voices are built for more than one language.
Can it copy a real person's voice?
No. Only the 41 preset voices are offered on this endpoint; there is no cloning and no upload of a reference voice.
What are the limits of the Seed Speech 2.0 API?
Text length (characters): 5,000; Voices: 41; Languages: 10. Requests outside these limits are rejected before anything is charged.
Can I try Seed Speech 2.0 without writing code?
Yes. The Playground runs Seed Speech 2.0 on your PopNow credits, needs no API key, and shows the matching code for every run.
Other audio APIs
- Gemini 3.8 Flash TTS APIExpressive speech that acts out cues like [laughing]From 0.05 credits per second
- MiniMax Speech 2.8 HD APIHigh-fidelity speech in 400+ voices with emotion controlFrom 18 credits per 1,000 characters
- Gemini 3.8 Flash-Lite TTS APIFast, lightweight speech in 30 voicesFrom 0.03 credits per second
- Grok TTS API71 voices across 20 languages with speech tagsFrom 3 credits per 1,000 characters
- MiniMax Speech 2.8 Turbo APIFast speech in 400+ voices with emotion controlFrom 11 credits per 1,000 characters
- Qwen3 TTS APIOpen-source speech with tone and pace set in plain wordsFrom 11 credits per 1,000 characters
