ElevenLabs Dialogue API

更新于2026年10月19日

What is ElevenLabs Dialogue?

ElevenLabs Dialogue is a multi-speaker audio endpoint that takes an array of {text, voice} turns and returns one combined audio file for the conversation. Up to 10 distinct ElevenLabs voices can appear in a single call, each turn picks any voice ID from your account (presets or clones), and the model handles the joins between turns so the result sounds like a real exchange rather than stitched TTS calls. The endpoint always uses the eleven_v3 model under the hood, so there is no model picker to manage. You control language via language_code (default en) and steadiness via stability (0 to 1). Inline emotion tags like [excitedly] or [whispered] at the start of a turn shape the delivery without any extra parameters.

Key features of ElevenLabs Dialogue

Five features cover what you'll set on a typical job.

What ElevenLabs Dialogue is best for

• Scripted podcasts

  Alternating hosts with distinct timbres in one API call. Inline emotion tags carry tone shifts without separate direction notes.

• Audiobook scenes

  Multiple cast voices for dialogue passages while the narrator stays on a different ElevenLabs voice. Mix in clones for branded narrator voices.

• Training simulators

  Role-play lines with fixed casting per character. Up to 10 voices fits a typical scenario script (customer, agent, supervisor, observer).

• Game NPC barks and short scenes

  Short turn-based dialogue between NPCs in a single render. Pair with a fixed stability to keep the cast tonally consistent across patches.

• Product walkthroughs

  Conversational two-host explainer instead of single-narrator voiceover. Reads as a podcast more than as a tutorial.

• Language learning dialogue

  Per-conversation stability for clarity in listening exercises. Switch language_code per scene to deliver content in the target language.

ElevenLabs text to speech or Dialogue: which endpoint do you need?

Many people reach this page from an "elevenlabs text to speech" search, so here is the split. ElevenLabs TTS reads one text in one voice and lets you choose among four models and 18 output formats. Dialogue takes a script with several speakers and returns one file with the handoffs already timed, always on eleven_v3. Eleven v4 does both in one model at a higher rate. Rates are UnificAlly's per 1,000 characters.

A real Dialogue output

Generated on October 19, 2026 through the UnificAlly MCP: four turns, two premade voices (Jessica cgSgspJ2msm6clMCkdW9 and Liam TX3LPaxmHKxFdv7VOQHJ), stability 0.5, language_code en, 351 characters of script including the tags, billed at $0.048/1000 characters per 1,000 characters.

The script, exactly as sent (each turn is one {text, voice} entry in the dialogue array):

• Jessica, [curiously]: "So the build passed on the first try? That never happens."
• Liam, [excitedly]: "First try. I rewrote the cache layer last night and every test went green this morning."
• Jessica, [warmly]: "Okay, that is genuinely impressive. Want to walk me through the diff before we ship it?"
• Liam, [whispered]: "Only if you promise not to find the bug I am pretty sure is still in there."

The result is 21.6 seconds of audio in one MP3, four handoffs included. Rendering the same four lines as separate TTS calls would give you four files to align and four different room tones; here the pauses between speakers come from the model.

ElevenLabs Dialogue use cases

Generate a podcast intro by writing a 4-turn dialogue between two hosts and dropping [warmly] and [excitedly] tags on the lines that need them. Build a compliance training scenario with three speakers (employee, customer, manager) and re-render with different stability values to A/B test how steady the cast should sound. Add an in-game dialogue system that batches NPC exchanges into single Dialogue calls so room tone matches across the scene. Localize a conversational explainer by switching language_code and the per-turn voice IDs while keeping the script structure constant.

ElevenLabs Dialogue API examples

Call ElevenLabs Dialogue from any language by POSTing to /v1/tasks. Full parameter docs live at docs.unifically.com/models/audio/elevenlabs/text-to-dialogue.

curl -X POST https://api.unifically.com/v1/tasks \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "elevenlabs/text-to-dialogue",
    "input": {
      "stability": 0.5,
      "language_code": "en",
      "dialogue": [
        {
          "text": "[excitedly] Hey Jessica! Have you tried the new ElevenLabs V3?",
          "voice": "TX3LPaxmHKxFdv7VOQHJ"
        },
        {
          "text": "[curiously] Yeah, just got it! The emotion is so amazing.",
          "voice": "cgSgspJ2msm6clMCkdW9"
        }
      ]
    }
  }'

Successful submission returns a task_id. Poll GET /v1/tasks/<task_id> or set a callback_url on the request to receive the finished audio URL.