Speechbase

Generate conversation

Synthesizes a multi-turn conversation into a single mixed audio file and returns the raw audio bytes. Set `split: true` to instead receive a JSON envelope with an `audioSegments` array, one entry per turn.

POST
/v1/audio/conversation

Synthesizes a multi-turn conversation into a single mixed audio file and returns the raw audio bytes. Set split: true to instead receive a JSON envelope with an audioSegments array, one entry per turn.

Authorization

bearerAuth
AuthorizationBearer <token>

API key

In: header

Request Body

application/json

TypeScript Definitions

Use the request body type in TypeScript.

Response Body

application/problem+json

application/problem+json

application/json

curl -X POST "https://example.com/v1/audio/conversation" \  -H "Authorization: Bearer $SPEECHBASE_API_KEY" \  -H "Content-Type: application/json" \  -d '{  "model": "openai/gpt-4o-mini-tts",  "turns": [    {      "voice": "alloy",      "text": "How was your weekend?"    },    {      "voice": "shimmer",      "text": "Good, I finally caught up on sleep."    }  ],  "gapMs": 500,  "output": "mp3"}'
{
  "audioSegments": [
    {
      "audio": "string",
      "mediaType": "string",
      "durationMs": 0,
      "turnIndex": 0
    }
  ],
  "warnings": [
    "string"
  ]
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "validation": [
    {
      "path": [
        "string"
      ],
      "message": "string"
    }
  ],
  "provider": "string",
  "upstream_code": "string",
  "upstream_status": 0,
  "turn_index": 0
}
{
  "type": "string",
  "title": "string",
  "status": 0,
  "detail": "string",
  "code": "string",
  "validation": [
    {
      "path": [
        "string"
      ],
      "message": "string"
    }
  ],
  "provider": "string",
  "upstream_code": "string",
  "upstream_status": 0,
  "turn_index": 0
}
{
  "error": {
    "code": "content_moderation_blocked",
    "message": "string",
    "reason": {
      "type": "error_fail_closed"
    }
  }
}

Generate speech with timestamps POST

Synthesizes speech and returns a JSON envelope with base64 audio and word-level timestamps. Pass either `voiceId` (to use a saved Voice) or `model` + `voice` (inline) — not both.

Generate conversation with timestamps POST

Synthesizes a multi-turn conversation and returns a JSON envelope with base64 audio and word-level timestamps mapped back to each originating turn. Set `split: true` to instead receive an `audioSegments` array, one entry per turn, each with block-relative timestamps.