curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "elevenlabs-v4-tts",
"input": {
"text": "Hello! Welcome to PoYo."
}
}
'
{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2026-10-13T10:30:00+08:00"
}
}ElevenLabs
ElevenLabs V4 TTS
Generate expressive speech with voice controls, 19 audio formats, and optional timestamps.
POST
/
api
/
generate
/
submit
curl --request POST \
--url https://api.poyo.ai/api/generate/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "elevenlabs-v4-tts",
"input": {
"text": "Hello! Welcome to PoYo."
}
}
'
{
"code": 200,
"data": {
"task_id": "task-unified-1757165031-uyujaw3d",
"status": "not_started",
"created_time": "2026-10-13T10:30:00+08:00"
}
}Submission returns a
task_id. Use Query Task Status to track completion, or supply callback_url for completion and failure notifications.
Parameters and combinations
text is required (1–5,000 characters). voice defaults to Rachel; use a supported voice name or voice ID.
stability defaults to 0.5 and similarity_boost to 0.75; both accept 0–1.
language_code is optional. apply_text_normalization accepts auto (default), on, or off. timestamps defaults to false and adds a separate timing JSON file when available.
output_format defaults to mp3_44100_128. Supported formats: mp3_22050_32, mp3_44100_32, mp3_44100_64, mp3_44100_96, mp3_44100_128, mp3_44100_192, pcm_8000, pcm_16000, pcm_22050, pcm_24000, pcm_44100, pcm_48000, ulaw_8000, alaw_8000, opus_48000_32, opus_48000_64, opus_48000_96, opus_48000_128, opus_48000_192.
MP3 and Opus are encoded audio; PCM is raw audio without a WAV header. µ-law and A-law are telephony formats. Output keeps its original encoding and file extension; use the selected sample rate when decoding raw audio.
Examples
{
"model": "elevenlabs-v4-tts",
"input": {
"text": "Hello! Welcome to PoYo."
}
}
{
"model": "elevenlabs-v4-tts",
"input": {
"text": "Welcome to PoYo.",
"timestamps": true,
"output_format": "pcm_24000"
}
}
Task results
The query response uses the common task structure:task_id, status, progress, files, and error_message. A finished task has status="finished"; each result file has file_url and file_type. Preserve the task ID while polling.
Speech appears as file_type="audio"; optional timing JSON appears as file_type="other".Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Body
application/json