Create speech

POST/v1/audio/speech

Convert text to spoken audio. The endpoint supports text-only generation, reference-audio generation, and reference-image generation when supported by the selected model.

Authentication

Authorization Bearer

API key as bearer token in Authorization header.

Request Body

inputstringrequired

Text input to synthesize into speech.

modelstringrequired

Model ID.

language_typestring

Speech language type.

speednumber

Speech speed adjustment.

referencesarray

Speech synthesis reference resources.

references.audio_urlstring

Reference audio URL.

references.image_urlstring

Reference image URL.

references.speakerstring

Provider speaker ID or cloned voice ID.

references.audio_datastring

Base64-encoded reference audio data.

references.image_datastring

Base64-encoded reference image data.

audio_configobject

Output audio configuration.

audio_config.formatstring

Output audio format.

audio_config.sample_rateinteger

Output audio sample rate in Hz.

audio_config.speech_ratenumber

Speech speed adjustment.

audio_config.pitch_ratenumber

Output pitch adjustment.

audio_config.loudness_ratenumber

Output loudness adjustment.

audio_formatstring

Output audio format.

rateinteger

Output audio sample rate in Hz.

loudness_rateinteger

Output loudness adjustment.

pitch_rateinteger

Output pitch adjustment.

watermarkobject

Watermark configuration.

watermark.aigc_watermarkboolean

Enable or disable the AIGC watermark.

watermark.aigc_metadataobject

AIGC metadata configuration.

response_formatstring

Response format.

metadataobject

Application metadata.

extra_bodyobject

Additional request body fields.

provider_optionsobject

Upstream configuration.

x_api_request_idstring

Upstream request ID.

Response

audiostring

Generated audio URL, or Base64-encoded audio if URL conversion is unavailable.

audio_typestring

How the audio field is encoded.

modelstring

Model used for synthesis.

voicestring

Provider voice identifier when available. Text-only requests may return a default voice value.

formatstring

Audio format.

sample_rateinteger

Sample rate in Hz.

usageobject

Usage and provider correlation details.

usage.audio_duration_secondsnumber

Generated audio duration used for billing when available. Provider duration metadata is used when available, falling back to post-processed duration.

usage.original_durationnumber

Original provider output duration in seconds.

usage.durationnumber

Post-processed audio duration in seconds.

usage.provider_request_idstring

Provider request ID used for upstream correlation.

Request

1curl -X POST https://api.token360.ai/v1/audio/speech \
2  -H "Authorization: Bearer sk-your-api-key" \
3  -H "Content-Type: application/json" \
4  -H "X-Api-Request-Id: seed-audio-text-only-001" \
5  -d '{
6    "model": "seed-audio-1.0",
7    "input": "Welcome to Token360, your unified AI gateway.",
8    "audio_format": "mp3",
9    "rate": 44100,
10    "speed": 0,
11    "loudness_rate": 0,
12    "pitch_rate": 0,
13    "response_format": "url"
14  }'

Response

JSON

1{
2  "audio": "your-audio-url",
3  "audio_type": "url",
4  "model": "seed-audio-1.0",
5  "voice": "default",
6  "format": "mp3",
7  "sample_rate": 44100,
8  "usage": {
9    "duration": 2.1,
10    "original_duration": 2.1,
11    "audio_duration_seconds": 2.1,
12    "provider_request_id": "seed-audio-text-only-001"
13  }
14}

Was this page helpful?