Speech Synthesis API Reference

OpenAI-compatible text-to-speech: one request synthesizes the whole audio clip and the response is raw audio bytes. Works with OpenAI TTS, Bailian Qwen-Audio-TTS, MiniMax and Volcengine speech models.

Field	Value
Base URL	`https://token.easyapi.com/v1`
Authentication	Authorization: Bearer `API_KEY`
Example model	`qwen-audio-3.0-tts-plus`
Format	REST JSON (audio bytes in response)
Billing	Priced by input characters / audio duration

Note: The response is not JSON but raw audio; Content-Type follows response_format: mp3 → audio/mpeg, wav → audio/wav, pcm → audio/pcm, opus → audio/ogg. Valid voices depend on the model: Bailian Qwen-Audio-TTS uses voices such as longanhuan_v3.6, OpenAI TTS uses alloy / nova, so check the model's voice list. Provider-specific parameters can be passed through metadata.

Example model

Examples below use qwen-audio-3.0-tts-plus (Qwen Audio TTS Plus). Replace model and adjust size, quality, etc. per console docs when switching models.

Create speech

POSThttps://token.easyapi.com/v1/audio/speech

Synthesize the input text and return audio bytes directly. Streaming is not supported yet: stream_format=sse is answered with the complete clip.

Request parameters

Name	In	Type	Required	Description
`Authorization`	header	string	Yes	EasyAPI API Key. Format: Bearer `API_KEY`
`Content-Type`	header	string	Yes	Always application/json

Request body

Name	Type	Required	Description
`model`	string	Yes	Speech model ID, e.g. qwen-audio-3.0-tts-plus, gpt-4o-mini-tts, tts-1
`input`	string	Yes	Text to synthesize; SSML / LaTeX supported where the model allows it
`voice`	string	Yes	Voice name, model-specific; Bailian defaults to longanhuan_v3.6
`response_format`	string	No	Audio encoding: mp3 (default), wav, pcm, opus
`speed`	number	No	Speed multiplier, mapped to Bailian rate (0.5–2.0) and clamped to that range
`instructions`	string	No	Synthesis instruction for dialect, emotion or role, mapped to Bailian instruction
`metadata`	object	No	Provider-native parameters passed through: volume(0-100), pitch(0.5-2.0), bit_rate(6-510, opus only), sample_rate, enable_ssml, word_timestamp_enabled, seed, language_hints, hot_fix, enable_aigc_tag; keys matching standard fields take precedence

Example

{
  "model": "qwen-audio-3.0-tts-plus",
  "input": "你好，欢迎使用 EasyAPI 语音合成。",
  "voice": "longanhuan_v3.6",
  "response_format": "mp3",
  "speed": 1.0,
  "instructions": "用轻松自然的语气朗读"
}

Response example

HTTP/1.1 200 OK
Content-Type: audio/mpeg
Content-Length: 258048

<二进制音频数据>

Status codes

Status code	Meaning	Description	Data model
`200`	OK	Audio bytes; Content-Type depends on response_format	`audio/*`
`400`	Bad request	Invalid parameter or rejected by upstream, e.g. unknown voice or empty text	`ErrorResponse`
`401`	Unauthorized	Missing or invalid API key	`ErrorResponse`
`402`	Insufficient quota	Account balance cannot cover this synthesis	`ErrorResponse`
`429`	Rate limited	Too many requests, retry later	`ErrorResponse`
`500`	Server error	Upstream or gateway failure, safe to retry	`ErrorResponse`

Response: The gateway measures the audio duration: billing uses input characters and output audio duration, falling back to audio size when the duration cannot be parsed.