# Seed Audio 1.0 MCP and API - Text to speech by ByteDance | FlyMy.AI

> Seed Audio 1.0 makes audio from a text prompt, in a preset voice or guided by up to three reference clips or a picture.

Page: https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/

MCP / Models / Voice, music and sound

# Seed Audio 1.0 MCP: audio from one text prompt

Seed Audio 1.0 makes audio from a text prompt, in a preset voice or guided by up to three reference clips or a picture. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

[Use Seed Audio 1.0](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#start) [Inputs and price](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#inputs)

No API key, from $0.0375 / run, Text to speech, ByteDance, Commercial use

$ YOUR NEXT RUN

Claude Code, Codex, Cursor, Any agent

## Use Seed Audio 1.0 in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

```
Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/bytedance-seed-audio-1-0.md. Help me connect the FlyMy.AI MCP to this assistant, then run Seed Audio 1.0 (flymyai/bytedance-seed-audio-1_0) for this task: Read this paragraph aloud with Seed Audio 1.0 in a calm, friendly voice and send me the audio file.
```

[Open FlyMy.AI](https://app.flymy.ai/new-agent) [Download brief](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0.md)

## What Seed Audio 1.0 does

Write the text to say, or describe the audio to make, in prompt, required, up to 1,000 characters: it is not limited to reading a text aloud. voice picks a preset voice by name (the letters after the name are the languages it speaks, such as stokie_en or kian_en_zh). audios takes up to three reference clips, each up to 30 seconds and 10 MB (WAV, MP3, PCM or Ogg Opus), that you point to in the prompt as @Audio1, @Audio2 and @Audio3; image is a reference picture of up to 10 MB (JPEG, PNG or WebP) and cannot be sent with audio clips. speed (0.5 to 2), pitch (-12 to 12 semitones) and volume (0.5 to 2) shape the delivery, multilingual suits non-English or mixed-language text and output_format is mp3 (the default), wav or ogg_opus. Outputs: audio and duration, its length in seconds. You do not set the length: it follows the text and the speed.

It is billed on what the run uses, by the minutes of audio made. The price shown before the run is held on your balance and is worked out from the length of the prompt at a slow pace that suits speech, so a description of a scene can make longer audio than its length suggests (the model refuses audio that is too long); you are charged what the run cost. It makes one audio per request, makes no music and does not take a cloned-voice id.

Use a real person's voice or photo as a reference only with their consent.

## Seed Audio 1.0 inputs

Every input of `flymyai/bytedance-seed-audio-1_0` as its live schema lists them. Returns `audio` (array), `duration` (string).

| Input | Type, values and default |
|---|---|
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-prompt) `prompt` | string required The text to say, or a description of the audio to make, up to 1,000 characters; point to reference clips as @Audio1, @Audio2 and @Audio3. $0.1875 per minute of audio made |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-voice) `voice` | string optional A preset voice name; the letters after the name are the languages it speaks. Names: stokie_en, vivi_mixed_en_zh_ja_es_id, mindy_en_es_id_pt_zh, kian_en_zh, cedric_en_zh, sophie_en_zh, jean_en_zh, magnus_en_zh, mabel_en_zh, nadia_en_zh, opal_en_zh, pearl_en_zh, quentin_en_zh, corinne_mixed_en_zh, esther_mixed_en_zh, lyla_mixed_en_zh, tracy_es_zh, sandy_es_mixed_en_zh, felix_zh, celeste_zh, monkey_king_zh. Left out, the model chooses |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-audios) `audios` | string optional Up to three reference audio clips, links or uploads, each up to 30 seconds and 10 MB (WAV, MP3, PCM or Ogg Opus), referred to in the prompt as @Audio1, @Audio2 and @Audio3; not together with image. Use a real person's voice only with their permission |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-image) `image` | file optional Allowed: image file, as a URL or upload A reference picture (JPEG, PNG or WebP, up to 10 MB), a link or an upload; not together with audios. Use a real person's photo only with their permission |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-speed) `speed` | number optional Allowed: 0.5 to 2 Default: `1` Speech speed, 0.5-2 (1 is normal); a slower speed makes a longer audio |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-pitch) `pitch` | integer optional Allowed: -12 to 12 Default: `0` Pitch shift in semitones, -12 to 12 (0 is normal; -12 is an octave lower) |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-volume) `volume` | number optional Allowed: 0.5 to 2 Default: `1` Volume, 0.5-2 (1 is normal) |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-multilingual) `multilingual` | boolean optional Default: `false` Use the multilingual variant of the model, which handles non-English and mixed-language text better |
| [#](https://flymy.ai/mcp/models/bytedance-seed-audio-1-0/#input-output_format) `output_format` | string optional Allowed: mp3, wav, ogg_opus Default: `mp3` File format: mp3 (the default), wav or ogg_opus |

## Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

**“Read this paragraph aloud with Seed Audio 1.0 in a calm, friendly voice and send me the audio file.”** runs `flymyai/bytedance-seed-audio-1_0`

**“Voice my product demo script with Seed Audio 1.0 a little slower and lower in pitch, and give me the audio file.”** runs `flymyai/bytedance-seed-audio-1_0`

**“Use Seed Audio 1.0 to say a line in the voice of the clip I attach, which is a recording of me.”** runs `flymyai/bytedance-seed-audio-1_0`

## Seed Audio 1.0 price

From $0.0375 per run, depending on prompt and speed. A run at the default settings costs $0.0975. A run costs $0.0375 to $0.195, depending on prompt and speed. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

[See usage pricing →](https://flymy.ai/pricing/)

## Call Seed Audio 1.0 from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

### From an agent, through the MCP

The agent calls `get_model_schema`, then `run_model` with:

```
{
  "endpoint_id": "flymyai/bytedance-seed-audio-1_0",
  "input": {
    "prompt": "Welcome to FlyMy.AI. Your order has shipped and arrives on Friday."
  }
}
```

### From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a `prediction_id`; read the result at `https://api.flymy.ai/api/v1/flymyai/bytedance-seed-audio-1_0/predict/async/result/?request_id=<prediction_id>`.

```
curl -X POST https://api.flymy.ai/api/v1/flymyai/bytedance-seed-audio-1_0/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Welcome to FlyMy.AI. Your order has shipped and arrives on Friday.'
```

## Questions about Seed Audio 1.0

**Do I need a ByteDance API key for Seed Audio 1.0?**

No. Seed Audio 1.0 runs on FlyMy.AI's account, so you need no ByteDance key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

**How much does Seed Audio 1.0 cost?**

From $0.0375 per run, depending on prompt and speed. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

**How do I use Seed Audio 1.0 in Claude Code, Codex or Cursor?**

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Read this paragraph aloud with Seed Audio 1.0 in a calm, friendly voice and send me the audio file." Your agent reads the inputs with get_model_schema and runs flymyai/bytedance-seed-audio-1_0 with run_model.

**What does Seed Audio 1.0 need as input?**

Seed Audio 1.0 requires prompt; it also takes 8 optional inputs, each listed on this page with its allowed values and default.

**Can I call Seed Audio 1.0 from my own code?**

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/bytedance-seed-audio-1_0/predict/async/ with your FlyMy.AI API key in the X-API-KEY header.

## More voice, music and sound models

Read text aloud, clone a voice from a short sample, turn lyrics or a prompt into a song, compose instrumentals, make sound effects from a description or for a video, or repair and extend a track.

### Seed Speech TTS 2.0

ByteDance's speech model: up to 5,000 characters read aloud in 41 voices, with a plain-words delivery note.

Text to speech / $0.0018 / run

Link: https://flymy.ai/mcp/models/bytedance-seed-speech-tts-2-0/

### Gemini 3.8 Flash TTS

Google's higher-fidelity speech model: narration and multi-character scripts in 30 voices, with style control.

Text to speech / about $0.0135 / min of speech

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-tts/

### Gemini 3.8 Flash-Lite TTS

The low-cost Gemini 3.8 speech model for high volume: read-aloud features and voice agents.

Text to speech / about $0.009 / min of speech

Link: https://flymy.ai/mcp/models/gemini-3-8-flash-lite-tts/

### Lyria 3.5

Google DeepMind's music model: full songs or instrumentals from a written brief.

Music / $0.10 / run

Link: https://flymy.ai/mcp/models/lyria-3-5-music/

### MiniMax Music 3

MiniMax's open-weights music model: lyrics and a style prompt in, a full song with vocals out.

Music / $0.002 / s

Link: https://flymy.ai/mcp/models/minimax-music-3/

### MiniMax Speech 2.8 HD

MiniMax's high-quality speech model: 332 voices, 40 languages, emotions and laughs written into the text.

Text to speech / $0.10 / 1,000 characters

Link: https://flymy.ai/mcp/models/minimax-speech-2-8-hd/

## Go to the source

[Seed Audio 1.0 in the playground →](https://app.flymy.ai/models/flymyai/bytedance-seed-audio-1_0), [Model endpoints in the docs →](https://docs.flymy.ai/api/models-endpoints), [Every model on FlyMy.AI →](https://flymy.ai/mcp/models/), [Every MCP in the catalog →](https://flymy.ai/mcp/#catalog), [Usage pricing →](https://flymy.ai/pricing/)

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.

---

For agents: the FlyMyAI operating guide (sign up, connect, run models, tools and agents) is https://flymy.ai/skill.md, and https://flymy.ai/llms.txt lists the other pages and the documentation.
